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. 102869
    Prev
    Next
    INDEX
    Explanations

    coding formulas

    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
     Caso
    -0.09
     případě
    -0.09
    Caso
    -0.09
     kaso
    -0.08
     摩
    -0.08
     eti
    -0.08
     locations
    -0.08
    _compute
    -0.07
     περίπτωση
    -0.07
     mantle
    -0.07
    POSITIVE LOGITS
     depletion
    0.08
     মান
    0.08
    apple
    0.08
     comparator
    0.07
    颖
    0.07
    written
    0.07
    NA
    0.07
    _FIL
    0.07
    sticky
    0.07
    _Value
    0.07
    Activations Density 0.002%

    No Known Activations