© 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. 22791
    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
    -0.09
     anabolic
    -0.08
    matig
    -0.08
     દરેક
    -0.08
    ыры
    -0.08
    pụta
    -0.08
     افز
    -0.08
    rị
    -0.08
     XHTML
    -0.08
    척
    -0.08
    POSITIVE LOGITS
     testimony
    0.12
     testimon
    0.12
     बयान
    0.12
     Jehov
    0.11
     publics
    0.11
     statement
    0.10
     statements
    0.10
     Protection
    0.10
     protection
    0.10
    Protection
    0.10
    Activations Density 0.006%
    No Known Activations