© 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. 71499
    Prev
    Next
    INDEX
    Explanations

    Math and logic problems

    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
    Not in Any Lists

    No Comments

    Negative Logits
     entsprechenden
    -0.09
     naquela
    -0.08
     daquele
    -0.08
     shopping
    -0.08
    ifiez
    -0.08
     considérer
    -0.08
    стал
    -0.07
     festen
    -0.07
    вар
    -0.07
     entsprechende
    -0.07
    POSITIVE LOGITS
     irrelevant
    0.17
     insignificant
    0.12
    ignored
    0.11
     बावजूद
    0.09
     moot
    0.09
     unrelated
    0.09
     meaningless
    0.09
     ignored
    0.09
    irre
    0.09
     inutile
    0.09
    Activations Density 0.058%

    No Known Activations