© 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. 22763
    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
     different
    -0.10
     each
    -0.10
     erine
    -0.09
     and
    -0.09
     diferents
    -0.09
     many
    -0.09
     différentes
    -0.09
     whether
    -0.09
     individu
    -0.08
     différents
    -0.08
    POSITIVE LOGITS
     Additional
    0.12
     अतिरिक्त
    0.12
     zusätzliche
    0.12
     zusätzlichen
    0.12
     adicionales
    0.12
     WOULD
    0.11
    額
    0.11
     adicionais
    0.11
     additional
    0.11
     dodatk
    0.11
    Activations Density 0.003%

    No Known Activations