© 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. 18187
    Prev
    Next
    INDEX
    Explanations

    margin

    np_max-act-logits · gemini-2.0-flash
    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
     Efter
    -0.09
     After
    -0.08
     verbinding
    -0.08
     Equipped
    -0.08
     uitgerust
    -0.08
     Kindly
    -0.08
     Après
    -0.08
     Dopo
    -0.08
     Após
    -0.07
     Spacious
    -0.07
    POSITIVE LOGITS
     duy
    0.09
     flush
    0.08
    flush
    0.08
     mostramos
    0.08
    .display
    0.08
    .level
    0.08
    ходим
    0.08
     consolidate
    0.08
    ，没有
    0.08
     no
    0.08
    Activations Density 0.001%

    No Known Activations