© 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. 29040
    Prev
    Next
    INDEX
    Explanations

    lists/instructions

    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
    ち
    -0.08
     yapılan
    -0.07
     bakt
    -0.07
     diin
    -0.07
     cie
    -0.07
    传播
    -0.07
    AMESPACE
    -0.07
     cosmos
    -0.07
     Ursprung
    -0.07
    赋
    -0.07
    POSITIVE LOGITS
     تجهيز
    0.13
     понадобится
    0.11
    oldoende
    0.11
    معدات
    0.11
     керек
    0.11
     мебели
    0.10
     комплект
    0.10
     જરૂરી
    0.10
     utensils
    0.10
     أدوات
    0.10
    Activations Density 0.040%

    No Known Activations