Scorecard/Goodfire

Goodfire

B

AI interpretability research lab using mechanistic interpretability to understand, audit, and steer AI model behavior for safer deployment.

HQUS
Est2024
Size11-50
EU AI ActLimited Risk
goodfire.ai
Score
56.3 / 100
Evidence
9 items

Strong safety posture with established governance frameworks and active risk management.

Strengths:Governance Maturity, Technical Safety, Risk Assessment, External Engagement
Weaknesses:Regulatory Readiness
Focus Areas
interpretabilityai safetymodel auditingalignment research

Dimension Breakdown

GM
Governance Maturitymedium
Published policies, corporate structure, safety mandate, whistleblowing, executive commitment.
55
2 evidence items
GM-01GM-02
TS
Technical Safetymedium
Benchmarks, adversarial robustness, fine-tuning safety, watermarking, model cards, research output.
72
2 evidence items
TS-01TS-02
RA
Risk Assessmentlow
Dangerous capability evaluations, thresholds, external testing, bug bounty, halt conditions.
55
2 evidence items
RA-01RA-08
RR
Regulatory Readinesslow
ISO 42001, EU AI Act compliance, GPAI obligations, international commitments, incident reporting.
30
EE
External Engagementmedium
Survey participation, research support, transparency, behavior specs, open-source contributions.
75
3 evidence items
EE-01EE-02EE-06

Need a detailed report for Goodfire?

Indicator-level evidence, peer benchmarking, regulatory gap analysis, and quarterly monitoring.