© 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. 8126
    Prev
    Next
    INDEX
    Explanations

    taxi fares

    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
     bugs
    -0.09
     actor
    -0.08
    aisseur
    -0.07
    bugs
    -0.07
    pec
    -0.07
    astr
    -0.07
    ąć
    -0.07
    mon
    -0.07
     Richie
    -0.07
    retro
    -0.07
    POSITIVE LOGITS
     kinetic
    0.08
     increases
    0.08
     ప్రారంభ
    0.08
     కథ
    0.08
     السين
    0.08
     zufrieden
    0.07
     الرك
    0.07
     والخ
    0.07
    .members
    0.07
     الاستخدام
    0.07
    Activations Density 0.008%

    No Known Activations