Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 109302
    Prev
    Next
    INDEX
    Explanations

    art, flattening shapes

    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
     backsplash
    -0.09
    二等奖
    -0.09
     roommates
    -0.09
    .reward
    -0.08
     lender
    -0.08
     Investors
    -0.08
     беше
    -0.08
     investors
    -0.08
     recompensa
    -0.08
    多少钱
    -0.08
    POSITIVE LOGITS
     obscure
    0.09
     grotes
    0.09
     अक्सर
    0.08
     violently
    0.08
    描
    0.08
    大量
    0.08
    .H
    0.08
    (dialog
    0.08
    (obs
    0.07
     dialog
    0.07
    Activations Density 0.033%

    No Known Activations