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. 74917
    Prev
    Next
    INDEX
    Explanations

    chutney dishes

    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
     mear
    -0.08
     dancing
    -0.08
     liking
    -0.08
     दौ
    -0.07
     लोग
    -0.07
     motions
    -0.07
     motion
    -0.07
    'D
    -0.07
     experiencing
    -0.07
     Latest
    -0.07
    POSITIVE LOGITS
    tion
    0.08
    уй
    0.08
     onderste
    0.07
     FW
    0.07
    ventory
    0.07
     extremist
    0.07
    önen
    0.07
     impover
    0.07
     Horton
    0.07
     smarty
    0.07
    Activations Density 0.001%

    No Known Activations