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. 8354
    Prev
    Next
    INDEX
    Explanations

    expected

    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
     envelop
    -0.08
     acronym
    -0.08
    己
    -0.08
    ையாள
    -0.07
    abcdef
    -0.07
     porter
    -0.07
     stereotypes
    -0.07
    istan
    -0.07
    assar
    -0.07
    ??
    -0.07
    POSITIVE LOGITS
    ാവ്
    0.09
     Sent
    0.08
     Alliance
    0.08
     fortune
    0.08
     Aufwand
    0.07
     Former
    0.07
     Stir
    0.07
     miesię
    0.07
     walkway
    0.07
    uerpo
    0.07
    Activations Density 0.003%

    No Known Activations