© 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. 102793
    Prev
    Next
    INDEX
    Explanations

    use

    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
    合法的吗
    -0.12
    <|reserved_200015|>
    -0.12
    -国产
    -0.12
    ырг
    -0.11
    助赢
    -0.11
    _国产
    -0.11
    久在线
    -0.11
    акә
    -0.11
     жүрг
    -0.11
    下载安装到
    -0.11
    POSITIVE LOGITS
     notion
    0.18
     idea
    0.18
     properties
    0.17
     fact
    0.17
     Tatsache
    0.17
     that
    0.17
     faptul
    0.16
     property
    0.16
     činjen
    0.16
     known
    0.16
    Activations Density 0.024%

    No Known Activations