© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 75647
    Prev
    Next
    INDEX
    Explanations

    Expertise and skill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Quoted
    -0.09
     trailer
    -0.09
    Tenant
    -0.08
    Announcements
    -0.08
    -header
    -0.08
    Trailer
    -0.08
    -0.08
    édio
    -0.07
    -slide
    -0.07
     provisions
    -0.07
    POSITIVE LOGITS
     विशेषज्ञ
    0.14
     mastery
    0.12
     ಪರಿಣ
    0.12
     Expertise
    0.11
    高手
    0.11
     expertise
    0.11
     experto
    0.11
    专家
    0.10
     excellence
    0.10
     Experten
    0.10
    Activations Density 0.026%
    No Known Activations