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. 112179
    Prev
    Next
    INDEX
    Explanations

    time

    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
     lura
    -0.08
     gepland
    -0.08
     видов
    -0.08
     заверш
    -0.08
     велич
    -0.08
    რთ
    -0.07
     cliffs
    -0.07
     Beige
    -0.07
     הקר
    -0.07
    ्यमंत्री
    -0.07
    POSITIVE LOGITS
     accurate
    0.09
    (se
    0.08
    .personal
    0.08
    WS
    0.08
    .se
    0.08
    /company
    0.08
     demographic
    0.07
     ರೂ
    0.07
     dém
    0.07
     einstellen
    0.07
    Activations Density 0.004%

    No Known Activations