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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 90814
    Prev
    Next
    INDEX
    Explanations

    File path delimiter

    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
    .XPATH
    -0.08
    _xpath
    -0.08
    .XPath
    -0.08
     eros
    -0.07
     replies
    -0.07
    angular
    -0.07
    .xpath
    -0.07
    ileged
    -0.07
    #if
    -0.07
    325
    -0.07
    POSITIVE LOGITS
     bescherm
    0.09
     moed
    0.08
    programma
    0.08
     Netherlands
    0.08
     hjælpe
    0.08
     مرسته
    0.08
    POL
    0.08
    ај
    0.08
    oude
    0.07
    onje
    0.07
    Activations Density 0.000%

    No Known Activations