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. 12071
    Prev
    Next
    INDEX
    Explanations

    count

    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
     difficulties
    -0.08
    tras
    -0.08
    penser
    -0.08
     sinus
    -0.07
    Salir
    -0.07
    apura
    -0.07
     longtime
    -0.07
     Ha
    -0.07
     difficulty
    -0.07
    .Push
    -0.07
    POSITIVE LOGITS
     occurrences
    0.10
     occurrence
    0.10
    聚
    0.10
     تعداد
    0.09
    Occurrences
    0.09
    (*)
    0.09
    _occ
    0.09
    /count
    0.09
     COUNT
    0.09
    (count
    0.09
    Activations Density 0.006%

    No Known Activations