Goodfire
Company goodfire.ai ● Covered in 6 stories + Follow ✴ AI Graph
Goodfire is an AI interpretability company developing tools and techniques to understand and control neural network internals through mechanistic interpretability methods. The company proposes intentional design approaches using semantic decomposition of networks to guide model training and published research on neural geometry, sparse autoencoders, and steering mechanisms across vision, language, and genomic models, with applications in reducing hallucinations, detecting rare failures, and enabling safety interventions.
Updated 7 August 2026
Signals
2 stories (new)
Media momentum
As of 17 Sep 2026 · Visible stories in the last 30 days, compared with the 30 days before.
3 sources
Source diversity
As of 17 Sep 2026 · Distinct publications behind this entity's visible coverage.
1 event
Release activity
As of 17 Sep 2026 · Model, product and open-source release events in the last 90 days whose coverage involves this entity.
—
Funding signals
As of 17 Sep 2026 · Funding and acquisition events in the last 90 days whose coverage involves this entity.
Jul 2026 → Sep 2026
Coverage span
As of 17 Sep 2026 · First to most recent month of TLDRocket coverage of this entity.
Management
updated 5 Aug 2026- Eric Ho Co-founder & CEO
- Archa Jain Head of Life Sciences
- Nathan Rourke Head of Finance
- Neboysa Omcikus COO
- Daniel Balsam Co-Founder and CTO
- Jackie Carlson Head Of People
Latest developments
Opening AI's Black Box: Understanding Neural Networks Through Interpretability
YouTube · 2 months ago ·
31
September 2026
August 2026
July 2026
Goodfire Silico launches interpretability platform and publishes neural geometry research for AI model analysis and control Product launch
Relationships
Products & technology
- Supplies Rakuten · 1 source
- Develops Silico · 1 source
- Integrated with Allen Institute for AI · 1 source