© 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. 109881
    Prev
    Next
    INDEX
    Explanations

    Comma

    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
    Bench
    -0.08
    speed
    -0.08
     Bench
    -0.08
    <R
    -0.07
    Sharp
    -0.07
    Soap
    -0.07
    soap
    -0.07
    one
    -0.07
    Rounds
    -0.07
    ones
    -0.07
    POSITIVE LOGITS
    elijkse
    0.09
     ago
    0.08
     hive
    0.08
     khale
    0.08
     tagasi
    0.08
     студент
    0.08
     Journalist
    0.08
     agli
    0.07
     taka
    0.07
    andidat
    0.07
    Activations Density 0.061%

    No Known Activations