© 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. 19-RESID-POST-AA
    11. 103038
    Prev
    Next
    INDEX
    Explanations

    .

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.14
     an
    -0.14
     a
    -0.13
    、
    -0.12
     ،
    -0.12
    ،
    -0.12
     some
    -0.11
     the
    -0.11
     ,
    -0.10
     in
    -0.10
    POSITIVE LOGITS
    <|reserved_200000|>
    0.12
    夫妻性生活影片
    0.11
     时时彩平台
    0.11
     天天爱彩票
    0.11
     曾道人
    0.11
    합뉴스
    0.11
    （责任编辑
    0.11
    久久综合久久爱
    0.11
    �็บ
    0.11
    ბილის
    0.11
    Activations Density 0.002%

    No Known Activations