© 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. 65022
    Prev
    Next
    INDEX
    Explanations

    .filter

    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
     �
    -0.09
    .proto
    -0.08
     çıktı
    -0.08
    .gradient
    -0.08
     direto
    -0.07
    되
    -0.07
     없음
    -0.07
    週間
    -0.07
    aryn
    -0.07
     ás
    -0.07
    POSITIVE LOGITS
    (&:
    0.08
     item
    0.08
    0.07
     aquela
    0.07
    bx
    0.07
     eduk
    0.07
     строки
    0.07
     amantes
    0.07
     qualcuno
    0.07
    Item
    0.07
    Activations Density 0.003%
    No Known Activations