© 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. 22922
    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
     a
    -0.12
     the
    -0.11
     an
    -0.11
     את
    -0.10
    _{
    -0.09
     awọn
    -0.09
     amely
    -0.08
     various
    -0.08
    	a
    -0.08
     ahol
    -0.08
    POSITIVE LOGITS
     nécessité
    0.09
     tâche
    0.09
     précédente
    0.09
     purposely
    0.09
    .problem
    0.09
     લખ
    0.09
    .mask
    0.09
     ####
    0.08
     ###
    0.08
     Writing
    0.08
    Activations Density 0.125%

    No Known Activations