© 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. 48486
    Prev
    Next
    INDEX
    Explanations

    <|start|>

    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
     ys
    -0.11
     yl
    -0.09
     yn
    -0.09
     vz
    -0.09
     yg
    -0.09
     rl
    -0.08
     顺
    -0.08
     erse
    -0.08
     yig
    -0.08
     za
    -0.08
    POSITIVE LOGITS
     commentary
    0.21
    <|channel|>
    0.21
    comment
    0.20
    analysis
    0.19
     Commentary
    0.17
    コメント
    0.16
    评论
    0.16
     comentario
    0.16
    COMMENT
    0.16
     commentaire
    0.16
    Activations Density 0.357%

    No Known Activations