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. 108975
    Prev
    Next
    INDEX
    Explanations

    generate

    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
    972
    -0.08
     жүрген
    -0.08
    qrt
    -0.08
     Merkur
    -0.08
     الرجال
    -0.08
     vrouwen
    -0.07
     महिल
    -0.07
    落实
    -0.07
     لارې
    -0.07
    irenze
    -0.07
    POSITIVE LOGITS
     conversational
    0.09
    ત્ર
    0.08
     extracts
    0.08
     Whats
    0.08
     WITHOUT
    0.08
     extracted
    0.08
     chants
    0.08
    Extract
    0.08
    flash
    0.08
     flash
    0.08
    Activations Density 0.013%

    No Known Activations