---
type: "Evidence Item"
title: "gpt-oss-safeguard technical report"
description: "gpt-oss-safeguard-120b and gpt-oss-safeguard-20b are two open-weight reasoning models post-trained from the gpt-oss models and trained to reason from a provided policy in order."
resource: "https://openai.com/index/gpt-oss-safeguard-technical-report"
tags: ["appendix-iii", "vendor", "openai"]
timestamp: "2025-10-29"
category: "vendor"
publisher: "OpenAI"
cope_score: 36
confidence: 0.9
---

# gpt-oss-safeguard technical report

# Claim

gpt-oss-safeguard-120b and gpt-oss-safeguard-20b are two open-weight reasoning models post-trained from the gpt-oss models and trained to reason from a provided policy in order to label content under that policy. In this report, we describe gpt-oss-safeguard’s capabilities and provide our baseline safety evaluations on the gpt-oss-safeguard models, using.

# Relevance

Appendix III, section two: vendor threshold and platform capability evidence

# Oracle Verdict

This is a low-signal vendor radar item. Keep it as context only unless a later benchmark, deployment, procurement change, or labour-market datapoint turns it into direct Appendix III evidence.

# Metadata

* Publisher: OpenAI
* Category: vendor
* Sector: Cybersecurity
* Capability: Vendor platform capability signal
* Cope score: 36
* Confidence: 0.9

# Related Concepts

* [Live evidence index](index.md)
* [Thesis](../thesis.md)

# Citations

[1] [gpt-oss-safeguard technical report](https://openai.com/index/gpt-oss-safeguard-technical-report)