© 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. 23-RESID-POST-AA
    11. 51954
    Prev
    Next
    INDEX
    Explanations

    ‑

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Spanish
    -0.10
     Latv
    -0.09
     татар
    -0.09
    азақ
    -0.08
     Тер
    -0.08
     Татар
    -0.08
     российских
    -0.08
     SPELL
    -0.08
     spanish
    -0.08
     Lithuan
    -0.08
    POSITIVE LOGITS
    keun
    0.17
    soeng
    0.16
     Ён
    0.16
    woo
    0.15
    heon
    0.14
     Woo
    0.14
    seo
    0.14
    young
    0.14
    -you
    0.14
    woon
    0.14
    Activations Density 0.038%

    No Known Activations