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. 94964
    Prev
    Next
    INDEX
    Explanations

    "─"

    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
    �
    -0.08
    örg
    -0.08
     sty
    -0.07
    Regardless
    -0.07
     encouragement
    -0.07
     Dow
    -0.07
    Walter
    -0.07
    168
    -0.07
    λύ
    -0.07
    βά
    -0.07
    POSITIVE LOGITS
     jiro
    0.08
     classific
    0.08
     recettes
    0.08
     belas
    0.08
     dedic
    0.07
     receitas
    0.07
     clasific
    0.07
    jd
    0.07
    .jd
    0.07
     novas
    0.07
    Activations Density 0.003%

    No Known Activations