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. 77486
    Prev
    Next
    INDEX
    Explanations

    ged

    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
    aum
    -0.08
     ggf
    -0.08
     વ્યવ
    -0.07
    એક
    -0.07
    ิล
    -0.07
     repert
    -0.07
     сод
    -0.07
     deme
    -0.07
     Stanton
    -0.07
     Pim
    -0.07
    POSITIVE LOGITS
     winter
    0.08
     ters
    0.08
     mountainous
    0.08
     jag
    0.07
    眉
    0.07
    青春
    0.07
    Gn
    0.07
     mountains
    0.07
    -ed
    0.07
     лини
    0.07
    Activations Density 0.003%

    No Known Activations