© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47157
    Prev
    Next
    INDEX
    Explanations

    Wines

    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
     facilita
    -0.08
     facilitating
    -0.08
    Req
    -0.08
     fandom
    -0.08
     downtime
    -0.07
     permanence
    -0.07
     يس
    -0.07
     мыш
    -0.07
    _req
    -0.07
     облегч
    -0.07
    POSITIVE LOGITS
     specimens
    0.09
    云南
    0.09
     Moroccan
    0.08
     제주
    0.08
    湖南
    0.08
     Tunis
    0.08
     Southern
    0.08
     ammon
    0.08
     aged
    0.08
     Assam
    0.08
    Activations Density 0.025%

    No Known Activations