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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 54155
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     jez
    -0.09
     stencil
    -0.08
     apar
    -0.08
     übertragen
    -0.08
     Noir
    -0.08
     parody
    -0.08
     Mene
    -0.08
     Brave
    -0.07
    GNU
    -0.07
    lieben
    -0.07
    POSITIVE LOGITS
    holiday
    0.08
    ター
    0.08
    ハ
    0.07
     "{\"
    0.07
     pamamagitan
    0.07
     holiday
    0.07
    $new
    0.07
    cid
    0.07
     specifies
    0.07
    snow
    0.07
    Activations Density 0.004%

    No Known Activations