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

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 38
    Prev
    Next
    INDEX
    Explanations

    midpoint

    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
     respective
    -0.09
    :↵↵↵
    -0.09
     fhèin
    -0.09
    펴
    -0.09
     ?>>↵
    -0.09
     ^^↵↵
    -0.09
     various
    -0.09
    umva
    -0.09
    ));↵↵↵
    -0.09
    !↵↵
    -0.09
    POSITIVE LOGITS
    -like
    0.08
    0.07
     surcharge
    0.07
     Michael
    0.07
     braking
    0.07
    ",↵
    0.06
     অত
    0.06
     mismatch
    0.06
    -direct
    0.06
    -met
    0.06
    Activations Density 0.032%

    No Known Activations