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. 119205
    Prev
    Next
    INDEX
    Explanations

    Command-line arguments/code

    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
     títulos
    -0.09
     payouts
    -0.08
     elderly
    -0.08
     Title
    -0.08
    Title
    -0.08
     rehab
    -0.08
     BLE
    -0.07
     Titles
    -0.07
     glitch
    -0.07
    PURE
    -0.07
    POSITIVE LOGITS
    =value
    0.09
     nargs
    0.09
     visionary
    0.09
    工业
    0.08
    他说
    0.08
    ಕ್
    0.08
     policym
    0.08
     ಕೊ
    0.08
    .split
    0.08
    -valu
    0.08
    Activations Density 0.005%

    No Known Activations