© 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. 110108
    Prev
    Next
    INDEX
    Explanations

    theme or topic

    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
     بها
    -0.08
    .refs
    -0.07
    ゲ
    -0.07
     Indi
    -0.07
     wurden
    -0.07
     +=
    -0.07
     operasyon
    -0.07
    .credentials
    -0.07
    lef
    -0.07
     않는
    -0.07
    POSITIVE LOGITS
     темы
    0.19
    主题
    0.18
    テーマ
    0.18
     topics
    0.18
     тема
    0.17
     themes
    0.17
     теме
    0.17
     тему
    0.16
     temática
    0.16
    Tema
    0.16
    Activations Density 0.089%

    No Known Activations