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. 129788
    Prev
    Next
    INDEX
    Explanations

    ar

    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
    链
    -0.08
     vending
    -0.08
     Flyers
    -0.08
     Volks
    -0.08
    -INF
    -0.07
    ادت
    -0.07
    >s
    -0.07
     bị
    -0.07
     vouchers
    -0.07
     reput
    -0.07
    POSITIVE LOGITS
    _gen
    0.09
    _)↵
    0.08
    fusion
    0.08
    _)
    0.08
    keep
    0.07
    freeze
    0.07
     बस
    0.07
    strip
    0.07
    _unique
    0.07
    enn
    0.07
    Activations Density 0.003%

    No Known Activations