© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 658
    Prev
    Next
    INDEX
    Explanations

    of

    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
     Smoking
    -0.09
    Smoking
    -0.08
    foam
    -0.08
     puff
    -0.08
     flames
    -0.08
    -haired
    -0.08
     silhouette
    -0.08
    agte
    -0.08
     kosten
    -0.08
    -painted
    -0.07
    POSITIVE LOGITS
     tonal
    0.10
    .key
    0.08
     бик
    0.08
     بلد
    0.08
     major
    0.08
     tón
    0.08
     trigo
    0.08
     ambayo
    0.08
     турында
    0.07
     мөл
    0.07
    Activations Density 0.016%

    No Known Activations