Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 88261
    Prev
    Next
    INDEX
    Explanations

    soft

    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
     processing
    -0.08
    .placeholder
    -0.08
     طال
    -0.08
    Processing
    -0.08
     �
    -0.07
     wig
    -0.07
    בט
    -0.07
     placeholder
    -0.07
    tegr
    -0.07
     storage
    -0.07
    POSITIVE LOGITS
     abroad
    0.12
    文化
    0.12
     문화
    0.12
     diplomacy
    0.12
     культур
    0.11
     дипломат
    0.11
     Abroad
    0.11
     관광
    0.11
     kulture
    0.11
    外交
    0.11
    Activations Density 0.025%

    No Known Activations