© 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. 11-RESID-POST-AA
    11. 110048
    Prev
    Next
    INDEX
    Explanations

    Language exercises

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Ceremony
    -0.08
     lieben
    -0.08
     fav
    -0.08
     practicality
    -0.08
     Tema
    -0.08
    .IT
    -0.08
     충분
    -0.08
     govor
    -0.08
    .fd
    -0.08
     Для
    -0.08
    POSITIVE LOGITS
     highlighted
    0.08
     נמצ
    0.08
     problematic
    0.08
    0.08
     spotted
    0.08
     marked
    0.08
     "***
    0.08
     suspect
    0.07
     נמצא
    0.07
     destacados
    0.07
    Activations Density 0.010%
    No Known Activations