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. 30227
    Prev
    Next
    INDEX
    Explanations

    Protein/genetic sequence positions

    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
     querying
    -0.09
     كال
    -0.08
     tutorial
    -0.08
    warz
    -0.08
    -query
    -0.08
     társ
    -0.08
     الاستخدام
    -0.07
    授
    -0.07
    وجل
    -0.07
    table
    -0.07
    POSITIVE LOGITS
     leuc
    0.09
    Ago
    0.08
     positions
    0.08
    angstrom
    0.08
     Och
    0.08
    xxx
    0.08
     mutations
    0.07
     panjang
    0.07
    Pear
    0.07
    長
    0.07
    Activations Density 0.003%

    No Known Activations