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. 49267
    Prev
    Next
    INDEX
    Explanations

    =

    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
     sera
    -0.08
    existent
    -0.08
     infert
    -0.07
    Certainly
    -0.07
    imitives
    -0.07
    hares
    -0.07
    ieno
    -0.07
    iedades
    -0.07
     ấy
    -0.07
    inement
    -0.07
    POSITIVE LOGITS
    公式
    0.12
     fórmula
    0.11
     Formel
    0.11
     formula
    0.10
    Formula
    0.10
     Formula
    0.10
    สูตร
    0.09
     सूत्र
    0.09
     formulas
    0.09
     fundamentally
    0.09
    Activations Density 0.052%

    No Known Activations