After the initial success of GLM-4.5-Air-Derestricted, we thought it would be interesting to try and Derestrict one of the most famously restrictive model which is gpt-oss-120b.
Our goal with this release is to provide a version of the model that removed refusal behaviors while maintaining the high-performance reasoning of the original gpt-oss-120b. This is unlike regular abliteration which often inadvertently "lobotomizes" the model.
To achieve this, Arli AI utilized Norm-Preserving Biprojected Abliteration, a refined technique pioneered by Jim Lai (grimjim). You can read the full technical breakdown in this article.
Why this matters:
Standard abliteration works by simply subtracting a "refusal vector" from the model's weights. While this works to uncensor a model, it is mathematically unprincipled. It alters the magnitude (or "loudness") of the neurons, destroying the delicate feature norms the model learned during training. This damage is why many uncensored models suffer from degraded logic or hallucinations.
How Norm-Preserving Biprojected Abliteration fixes it:
This model was modified using a three-step approach that removes refusals without breaking the model's brain:
Biprojection (Targeting): We refined the refusal direction to ensure it is mathematically orthogonal to "harmless" directions. This ensures that when we cut out the refusal behavior, we do not accidentally cut out healthy, harmless concepts.
Decomposition: Instead of a raw subtraction, we decomposed the model weights into Magnitude and Direction.
Norm-Preservation: We removed the refusal component solely from the directional aspect of the weights, then recombined them with their original magnitudes.
The Result:
By preserving the weight norms, we maintain the "importance" structure of the neural network. Benchmarks suggest that this method avoids the "Safety Tax"—not only effectively removing refusals but potentially improving reasoning capabilities over the baseline, as the model is no longer wasting compute resources on suppressing its own outputs.
In fact, you may find surprising new knowledge and capabilities that the original model does not initially expose.
For gpt-oss-120b, we found that it might still occasionally try and suppress requests but eventually reason that it is unneccesary.
Welcome to the gpt-oss series, OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
We’re releasing two flavors of these open models:
gpt-oss-120b — for production, general purpose, high reasoning use cases that fit into a single 80GB GPU (like NVIDIA H100 or AMD MI300X) (117B parameters with 5.1B active parameters)
gpt-oss-20b — for lower latency, and local or specialized use cases (21B parameters with 3.6B active parameters)
Both models were trained on our harmony response format and should only be used with the harmony format as it will not work correctly otherwise.
[!NOTE]
This model card is dedicated to the larger gpt-oss-120b model. Check out gpt-oss-20b for the smaller model.
Highlights
Permissive Apache 2.0 license: Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment.
Configurable reasoning effort: Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.
Full chain-of-thought: Gain complete access to the model’s reasoning process, facilitating easier debugging and increased trust in outputs. It’s not intended to be shown to end users.
Fine-tunable: Fully customize models to your specific use case through parameter fine-tuning.
Agentic capabilities: Use the models’ native capabilities for function calling, web browsing, Python code execution, and Structured Outputs.
MXFP4 quantization: The models were post-trained with MXFP4 quantization of the MoE weights, making gpt-oss-120b run on a single 80GB GPU (like NVIDIA H100 or AMD MI300X) and the gpt-oss-20b model run within 16GB of memory. All evals were performed with the same MXFP4 quantization.
Inference examples
Transformers
You can use gpt-oss-120b and gpt-oss-20b with Transformers. If you use the Transformers chat template, it will automatically apply the harmony response format. If you use model.generate directly, you need to apply the harmony format manually using the chat template or use our openai-harmony package.
To get started, install the necessary dependencies to setup your environment:
pip install -U transformers kernels torch
Once, setup you can proceed to run the model by running the snippet below:
vLLM recommends using uv for Python dependency management. You can use vLLM to spin up an OpenAI-compatible webserver. The following command will automatically download the model and start the server.
