© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47207
    Prev
    Next
    INDEX
    Explanations

    once

    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
     avenues
    -0.08
     Hem
    -0.08
     sili
    -0.08
     ’
    -0.08
     ZZ
    -0.07
     soil
    -0.07
    مل
    -0.07
    ั
    -0.07
     HOR
    -0.07
    ’idée
    -0.07
    POSITIVE LOGITS
    Shop
    0.08
    名稱
    0.08
    ologi
    0.08
     Shirley
    0.08
     notor
    0.08
    Wiki
    0.08
    යන්
    0.08
    shops
    0.08
     nazw
    0.08
    Deferred
    0.07
    Activations Density 0.034%

    No Known Activations