© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18129
    Prev
    Next
    INDEX
    Explanations

    say <|return|>

    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
    Negative Logits
    。所以
    -0.09
    ,the
    -0.09
    ,j
    -0.09
    ，所以
    -0.08
    谁
    -0.08
     let's
    -0.08
    ,left
    -0.08
    !!)↵
    -0.08
    ,s
    -0.08
    ,i
    -0.07
    POSITIVE LOGITS
    <|return|>
    0.11
     Please
    0.11
    お願い
    0.10
     અથવા
    0.09
    Please
    0.09
    谢谢
    0.09
     courte
    0.09
    Thank
    0.09
    ありがとうございます
    0.09
     부탁
    0.09
    Activations Density 0.005%

    No Known Activations