© 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. 23063
    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
     Regardless
    -0.09
    يلية
    -0.09
     নতুন
    -0.09
     nuove
    -0.09
     независимо
    -0.09
    Regardless
    -0.09
    _IMPLEMENT
    -0.08
    、新
    -0.08
     implementar
    -0.08
     незалеж
    -0.08
    POSITIVE LOGITS
     remove
    0.13
    Remove
    0.13
    _remove
    0.13
    .remove
    0.13
     Remove
    0.12
     removing
    0.11
     =
    0.11
    remove
    0.11
     omit
    0.11
    (remove
    0.10
    Activations Density 0.009%

    No Known Activations