© 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. 29400
    Prev
    Next
    INDEX
    Explanations

    exchange

    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
    teger
    -0.08
    acle
    -0.08
     wächst
    -0.07
    .Roll
    -0.07
    MITTED
    -0.07
    sia
    -0.07
     derived
    -0.07
     gefunden
    -0.07
     Komm
    -0.07
     проведения
    -0.07
    POSITIVE LOGITS
     kepada
    0.10
     لنا
    0.10
     jums
    0.09
     لك
    0.09
     לכם
    0.09
    诸
    0.09
    东西
    0.08
     לך
    0.08
     لكم
    0.08
     näky
    0.08
    Activations Density 0.074%

    No Known Activations