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. 15-RESID-POST-AA
    6. 19536
    Prev
    Next
    INDEX
    Explanations

    end token

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     הראש
    -0.08
     cuando
    -0.08
    ('<
    -0.07
     ayi
    -0.07
    ('
    -0.07
     offen
    -0.07
     it
    -0.07
     any
    -0.07
     ale
    -0.07
    (/[
    -0.07
    POSITIVE LOGITS
    รั่ง
    0.09
     stance
    0.09
    Một
    0.08
    юм
    0.08
    โมสร
    0.08
    ัป
    0.08
     verden
    0.08
    ল্ল
    0.08
    араз
    0.08
    तीय
    0.08
    Activations Density 0.019%

    No Known Activations