© 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. 23112
    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
    .↵↵
    -0.10
    :↵↵
    -0.09
     needed
    -0.09
     catered
    -0.09
    :")↵
    -0.09
     tarvitse
    -0.09
    :none
    -0.09
    ?:
    -0.09
     against
    -0.09
    ,
    -0.09
    POSITIVE LOGITS
     normalize
    0.12
    Normalize
    0.11
     Normalize
    0.11
    normalize
    0.10
     sanitize
    0.09
    Ensure
    0.09
     Ensure
    0.09
     truncate
    0.09
     sigmoid
    0.08
     throttle
    0.08
    Activations Density 0.006%

    No Known Activations