© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 6263
    Prev
    Next
    INDEX
    Explanations

    say "query"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    一等奖
    -0.08
    ardonnay
    -0.08
     Wel
    -0.07
    ellular
    -0.07
    二等奖
    -0.07
    resso
    -0.07
     newborn
    -0.07
     Tet
    -0.07
    Importer
    -0.07
     الكهربائية
    -0.07
    POSITIVE LOGITS
     query
    0.34
    	query
    0.30
    query
    0.30
    _query
    0.29
    Query
    0.29
    .query
    0.28
     Query
    0.28
    (query
    0.28
    _QUERY
    0.27
     QUERY
    0.27
    Activations Density 0.031%

    No Known Activations