Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 88087
    Prev
    Next
    INDEX
    Explanations

    power, wealth

    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
     inventive
    -0.09
     riječ
    -0.08
     કાર્ય
    -0.08
    _keyword
    -0.08
     archa
    -0.08
     behoren
    -0.08
     પોત
    -0.08
    municip
    -0.08
     sweating
    -0.08
     KU
    -0.07
    POSITIVE LOGITS
     drog
    0.08
    {}{
    0.08
     Anliegen
    0.08
     Style
    0.08
     adot
    0.07
     aventuras
    0.07
     Wunsch
    0.07
     abundance
    0.07
     Wesen
    0.07
     disadvantage
    0.07
    Activations Density 0.000%

    No Known Activations