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. 119387
    Prev
    Next
    INDEX
    Explanations

    ellipse

    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
     scraped
    -0.08
     المشار
    -0.08
     olor
    -0.08
     Sher
    -0.08
    __':↵
    -0.07
    Barr
    -0.07
    _positive
    -0.07
    eyn
    -0.07
    Uploaded
    -0.07
     crude
    -0.07
    POSITIVE LOGITS
     maag
    0.08
     પોત
    0.08
    ғас
    0.07
    seid
    0.07
    �?
    0.07
     xog
    0.07
     swoje
    0.07
    зо
    0.07
     covariance
    0.07
     pusat
    0.07
    Activations Density 0.026%

    No Known Activations