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. 48760
    Prev
    Next
    INDEX
    Explanations

    dash/hyphen

    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
     Directorate
    -0.08
     hands
    -0.08
     ഇംഗ്ല
    -0.08
     cuck
    -0.08
     europe
    -0.08
    德国
    -0.08
    Hands
    -0.08
    Deutschland
    -0.08
     otr
    -0.08
    Doctrine
    -0.08
    POSITIVE LOGITS
     কাল
    0.08
     Gep
    0.08
     Lack
    0.08
     nong
    0.08
     jol
    0.07
     Retrouvez
    0.07
     Bail
    0.07
    .nil
    0.07
    .rev
    0.07
    kle
    0.07
    Activations Density 0.003%

    No Known Activations