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. 48938
    Prev
    Next
    INDEX
    Explanations

    question marks

    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
    004
    -0.08
    .path
    -0.08
     aiding
    -0.08
     Lawrence
    -0.07
    _path
    -0.07
     largely
    -0.07
    _Path
    -0.07
    .le
    -0.07
     encouraging
    -0.07
     helping
    -0.07
    POSITIVE LOGITS
    ???↵↵
    0.09
     вместо
    0.08
    depending
    0.08
    ?!↵
    0.08
    ??↵
    0.08
     Accounting
    0.08
     ???↵↵
    0.08
     yanlış
    0.08
    €↵↵
    0.07
    heben
    0.07
    Activations Density 0.087%

    No Known Activations