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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 30176
    Prev
    Next
    INDEX
    Explanations

    Programming code

    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
    急
    -0.08
     insist
    -0.08
     invest
    -0.08
     tiên
    -0.08
    -0.07
     precautions
    -0.07
     investir
    -0.07
    养
    -0.07
     pi
    -0.07
     pr
    -0.07
    POSITIVE LOGITS
    .prototype
    0.10
    .from
    0.09
    Utils
    0.08
    ന്റെ
    0.08
    ನ
    0.08
     객체
    0.08
    .defer
    0.08
    Stamped
    0.08
    (QObject
    0.08
    Manipulator
    0.08
    Activations Density 0.067%
    No Known Activations