© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 64655
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
    .average
    -0.08
     sucked
    -0.08
     평균
    -0.08
    平均
    -0.08
    Average
    -0.08
     Zür
    -0.08
     전화
    -0.08
    average
    -0.08
     گیری
    -0.08
    .Chat
    -0.08
    POSITIVE LOGITS
     royalty
    0.11
     license
    0.10
     ownership
    0.10
     лиценз
    0.10
     copyright
    0.10
     legally
    0.10
     warranties
    0.10
     allowance
    0.10
     الاستخدام
    0.10
     अधिकार
    0.10
    Activations Density 0.007%

    No Known Activations