© 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. 71529
    Prev
    Next
    INDEX
    Explanations

    press

    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
    ự
    -0.08
     principale
    -0.08
    okwa
    -0.08
     제외
    -0.07
     Europ
    -0.07
     Explorer
    -0.07
    忧
    -0.07
     planej
    -0.07
    οι
    -0.07
     المتعلقة
    -0.07
    POSITIVE LOGITS
    ింగ్
    0.08
     mos
    0.08
     মারা
    0.07
    (sig
    0.07
    ్చ
    0.07
     blows
    0.07
    -up
    0.07
    -step
    0.07
     quick
    0.07
     chats
    0.07
    Activations Density 0.003%

    No Known Activations