© 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. 22853
    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
    qq
    -0.08
    isar
    -0.08
     ontwerp
    -0.08
    �
    -0.08
     ডিজ
    -0.08
     electrician
    -0.08
     jolie
    -0.08
    miners
    -0.08
     convince
    -0.08
    -liked
    -0.08
    POSITIVE LOGITS
     разных
    0.09
     međ
    0.09
     '
    0.08
     surrounding
    0.08
     sides
    0.08
     γύ
    0.08
     that
    0.08
     đều
    0.08
     &___
    0.08
     forskjellige
    0.08
    Activations Density 0.008%

    No Known Activations