© 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. 99375
    Prev
    Next
    INDEX
    Explanations

    red

    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
     Military
    -0.08
     воздуш
    -0.08
    ект
    -0.08
     Perkins
    -0.08
     военно
    -0.07
     поля
    -0.07
     фрон
    -0.07
    (front
    -0.07
     Elon
    -0.07
     एड
    -0.07
    POSITIVE LOGITS
     darker
    0.09
    收藏
    0.08
     savory
    0.08
    જબ
    0.08
     dels
    0.07
     zbir
    0.07
     hearty
    0.07
    passport
    0.07
     pen
    0.07
     Brotherhood
    0.07
    Activations Density 0.003%

    No Known Activations