© 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. 130
    Prev
    Next
    INDEX
    Explanations

    Patagonia and sustainability

    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
     Fire
    -0.08
     felicit
    -0.08
     mi
    -0.08
     ign
    -0.08
     firing
    -0.08
    amman
    -0.07
     kvar
    -0.07
     kook
    -0.07
     Salaam
    -0.07
     papel
    -0.07
    POSITIVE LOGITS
    先锋
    0.09
    年度
    0.09
    াইন
    0.08
     distrust
    0.08
    年份
    0.08
    巨
    0.08
     paranoia
    0.08
    (inplace
    0.08
     gigantes
    0.08
    /...
    0.08
    Activations Density 0.001%

    No Known Activations