© 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. 18100
    Prev
    Next
    INDEX
    Explanations

    document

    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
     konke
    -0.09
    -uile
    -0.09
     എല്ല
    -0.09
     เซ
    -0.09
     hvert
    -0.08
     lahat
    -0.08
     ito
    -0.08
     Flere
    -0.08
     teljes
    -0.08
    -components
    -0.08
    POSITIVE LOGITS
    .query
    0.11
    .create
    0.10
    query
    0.09
    Creating
    0.09
    _query
    0.09
    查询
    0.09
     inserting
    0.09
     query
    0.08
    Query
    0.08
    Appending
    0.08
    Activations Density 0.001%

    No Known Activations