© 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. 22868
    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
    isho
    -0.09
     الجمع
    -0.08
    yclic
    -0.08
    arrage
    -0.08
    ieces
    -0.08
    ებიც
    -0.08
     Others
    -0.08
     صي
    -0.08
     dake
    -0.08
     شركات
    -0.08
    POSITIVE LOGITS
    在哪
    0.18
     dónde
    0.17
     at
    0.16
     where
    0.15
     into
    0.15
    Dónde
    0.15
     où
    0.15
     in
    0.14
     hvilken
    0.14
     waarop
    0.13
    Activations Density 0.029%

    No Known Activations