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. 46241
    Prev
    Next
    INDEX
    Explanations

    content submission

    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
     satis
    -0.08
     Eating
    -0.08
     отдыха
    -0.08
     Toshiba
    -0.08
     мыш
    -0.08
    -wire
    -0.08
     напряж
    -0.08
     Haush
    -0.08
    用品
    -0.08
     Zuf
    -0.07
    POSITIVE LOGITS
     référencement
    0.15
    传播
    0.15
     dissemination
    0.14
     backlinks
    0.14
    曝光
    0.14
     SEO
    0.13
     نشر
    0.13
    发布
    0.13
     publicar
    0.13
    掲載
    0.13
    Activations Density 0.096%

    No Known Activations