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. 54020
    Prev
    Next
    INDEX
    Explanations

    Seafood

    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
     Ferrari
    -0.08
    .jetbrains
    -0.08
    ZERO
    -0.08
    ňky
    -0.08
    oy
    -0.07
    )>>
    -0.07
     yr
    -0.07
    ויב
    -0.07
    ofy
    -0.07
     Housewives
    -0.07
    POSITIVE LOGITS
    (Size
    0.08
     batting
    0.08
     أكبر
    0.07
    Stuff
    0.07
     alam
    0.07
     Aggregate
    0.07
    mals
    0.07
    bab
    0.07
    ,包括
    0.07
     Aggreg
    0.07
    Activations Density 0.003%

    No Known Activations