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. 45114
    Prev
    Next
    INDEX
    Explanations

    square roots

    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
     велики
    -0.07
     entire
    -0.07
     بغ
    -0.07
     rango
    -0.07
     fleurs
    -0.07
     ranks
    -0.07
     tui
    -0.07
     Entire
    -0.07
    _i
    -0.07
     cicl
    -0.07
    POSITIVE LOGITS
     entsprechenden
    0.08
     Meghalaya
    0.08
     करव
    0.08
     entsprechende
    0.08
    ാക്കിയ
    0.08
     Malawi
    0.08
     Volleyball
    0.08
     snug
    0.08
    塘
    0.08
     teeb
    0.08
    Activations Density 0.024%

    No Known Activations