© 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. 22792
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     太阳城
    -0.11
     天天爱
    -0.11
    黑彩
    -0.10
    香港马会
    -0.10
     天逸
    -0.10
     极速赛车
    -0.10
    合法的吗
    -0.10
    马报
    -0.10
    红黑大战
    -0.10
     圣亚
    -0.10
    POSITIVE LOGITS
     wisely
    0.15
     relentlessly
    0.14
    ,
    0.14
     with
    0.13
     accordingly
    0.13
     your
    0.13
    ،
    0.13
     Accordingly
    0.13
    !:
    0.12
     responsibly
    0.12
    Activations Density 0.053%

    No Known Activations