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. 11964
    Prev
    Next
    INDEX
    Explanations

    packing lunches

    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
    技
    -0.08
     DHCP
    -0.08
     consensus
    -0.08
    Ÿ
    -0.08
    řízení
    -0.07
     viscosity
    -0.07
    技术
    -0.07
    .pag
    -0.07
     techni
    -0.07
    .Pages
    -0.07
    POSITIVE LOGITS
     lunches
    0.11
     lunch
    0.10
     koelkast
    0.09
     Portable
    0.09
    Portable
    0.08
     Lunch
    0.08
    Deadline
    0.08
     киш
    0.08
    ака
    0.08
     mahl
    0.08
    Activations Density 0.027%

    No Known Activations