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. 77576
    Prev
    Next
    INDEX
    Explanations

    pencils and office supplies

    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
     Thess
    -0.08
     immobil
    -0.07
     QT
    -0.07
     QS
    -0.07
     acelerar
    -0.07
     gated
    -0.07
    베
    -0.07
    亿美元
    -0.07
    tp
    -0.07
     vacant
    -0.07
    POSITIVE LOGITS
     workbook
    0.11
    -pencil
    0.11
     قلم
    0.11
     pencils
    0.11
    作文
    0.10
     pencil
    0.10
     الدراسي
    0.10
    /student
    0.10
     scolaire
    0.10
     ছাত্র
    0.09
    Activations Density 0.018%

    No Known Activations