© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 99498
    Prev
    Next
    INDEX
    Explanations

    unsplash image URLs

    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
     થઈ
    -0.09
    ¢
    -0.09
    цел
    -0.08
     терапии
    -0.08
    _IP
    -0.08
    (pl
    -0.08
    子
    -0.08
     FLASH
    -0.08
    子的
    -0.07
    groepen
    -0.07
    POSITIVE LOGITS
    stä
    0.08
     intemp
    0.07
    140
    0.07
    Fue
    0.07
     Pinterest
    0.07
    ilian
    0.07
    .emit
    0.07
    Rob
    0.07
     progrès
    0.07
    Night
    0.07
    Activations Density 0.003%

    No Known Activations