© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129366
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    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
    inas
    -0.08
     ал
    -0.08
    .exercise
    -0.08
    有关
    -0.08
    _about
    -0.08
    关于
    -0.07
    िग
    -0.07
     Ä
    -0.07
    航空
    -0.07
     Vivo
    -0.07
    POSITIVE LOGITS
     الجودة
    0.08
     instellingen
    0.08
     redact
    0.08
     kalite
    0.07
    946
    0.07
    наче
    0.07
    زام
    0.07
     الامر
    0.07
     بھی
    0.07
     oms
    0.07
    Activations Density 0.003%

    No Known Activations