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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 111605
    Prev
    Next
    INDEX
    Explanations

    need

    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
    Indexer
    -0.08
    ಾಣಿ
    -0.07
    ..)
    -0.07
     connaissez
    -0.07
    enga
    -0.07
    paq
    -0.07
    .Board
    -0.07
     saver
    -0.07
     পরীক্ষা
    -0.07
    ckte
    -0.07
    POSITIVE LOGITS
     mandated
    0.09
     полноцен
    0.08
    ות
    0.08
     obligations
    0.08
     उल्लेख
    0.08
     basically
    0.07
    distinct
    0.07
     uppercase
    0.07
     mention
    0.07
    ístico
    0.07
    Activations Density 0.045%

    No Known Activations