# OpenAI — gpt-oss-safeguard technical report

- Company: OpenAI (openai.com)
- Announced: 2025-10-29T00:00:00+00:00
- Category: new-model
- Subject: GPT / ChatGPT / API
- Open weights: yes
- Models affected: gpt-oss-safeguard-120b, gpt-oss-safeguard-20b, gpt-oss
- Source: https://openai.com/index/gpt-oss-safeguard-technical-report
- Record: https://forck.live/items/404-gpt-oss-safeguard-technical-report

OpenAI released two open-weight reasoning models, gpt-oss-safeguard-120b and gpt-oss-safeguard-20b, post-trained from the gpt-oss models to label content under a provided policy.

## Evidence

Verbatim from https://openai.com/index/gpt-oss-safeguard-technical-report:

> 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.

---

Record: https://forck.live/items/404-gpt-oss-safeguard-technical-report
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md