© 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. 75677
    Prev
    Next
    INDEX
    Explanations

    title

    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
     đi
    -0.08
     interest
    -0.08
     Babies
    -0.07
     Family
    -0.07
     repayment
    -0.07
     empowerment
    -0.07
     excited
    -0.07
     interess
    -0.07
    ('*
    -0.07
     Sur
    -0.07
    POSITIVE LOGITS
    <style
    0.09
    ită
    0.08
    /favicon
    0.08
     beziehungsweise
    0.08
    éget
    0.08
     Kabel
    0.08
     Arial
    0.08
     sift
    0.08
     šir
    0.08
     lato
    0.08
    Activations Density 0.001%

    No Known Activations