Blog - Goodfire

Blog

Announcing our SOC 2 Type II Certification

May 22, 2026

go to blog post

Interpretability Infrastructure at Frontier Scale: Harvesting Activations from a Trillion-Parameter Model

Michael Anderson, Michael Byun, Tucker Fross
February 25, 2026

go to blog post

Intentionally Designing the Future of AI

Thomas McGrath
February 5, 2026

go to blog post

Understanding, Learning From, and Designing AI: Our Series B

February 5, 2026

go to blog post

Stanford Guest Lectures: AP293 (Fall 2025)

December 11, 2025

go to blog post

Announcing Goodfire’s Fellowship Program for Interpretability Research

October 9, 2025

go to blog post

You and Your Research Agent: Lessons From Using Agents for Interpretability Research

Mark Bissell, Michael Byun, Daniel Balsam
October 2, 2025

go to blog post

Goodfire Announces Collaboration to Advance Genomic Medicine with AI Interpretability

September 9, 2025

go to blog post

Partnering with Radical AI to Advance Materials Science With Interpretability

July 30, 2025

go to blog post

On Optimism for Interpretability

Eric Ho
July 17, 2025

.jpg)
go to blog post

Announcing Our $50M Series A to Advance AI Interpretability Research

Eric Ho
April 17, 2025

go to blog post

Announcing Open-Source SAEs for Llama 3.3 70B and Llama 3.1 8B

Daniel Balsam, Thomas McGrath, Liv Gorton, Nam Nguyen, Myra Deng
January 10, 2025

go to blog post

Our Approach to Safety at Goodfire

Thomas McGrath
December 23, 2024

go to blog post

Feature Steering for Reliable and Expressive AI Engineering

Eric Ho
November 20, 2024

go to blog post