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. 15-RESID-POST-AA
    6. 14
    Prev
    Next
    INDEX
    Explanations

    find

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prestige
    -0.09
    .Vertex
    -0.08
     Олим
    -0.08
     만든
    -0.08
     mim
    -0.08
    ้ม
    -0.08
     recre
    -0.08
     olímp
    -0.08
     Judges
    -0.08
     ях
    -0.08
    POSITIVE LOGITS
    .search
    0.15
     grep
    0.15
    検索
    0.15
     searching
    0.14
    搜索
    0.14
    (search
    0.14
     поиска
    0.14
    Searching
    0.13
    -search
    0.13
     Searching
    0.13
    Activations Density 0.007%

    No Known Activations