© 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. 22999
    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
    Negative Logits
     Ensure
    -0.10
     improved
    -0.09
     tóp
    -0.09
     ખાત
    -0.08
     whenever
    -0.08
     whatever
    -0.08
     asegura
    -0.08
     համոզ
    -0.08
    确保
    -0.08
     ensure
    -0.08
    POSITIVE LOGITS
     diferenças
    0.17
     Unterschiede
    0.17
     differs
    0.16
     differences
    0.16
     differ
    0.16
     différences
    0.16
     Differences
    0.15
     verschillen
    0.15
     unterscheiden
    0.15
     diferencias
    0.15
    Activations Density 0.073%

    No Known Activations