Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 30789
    Prev
    Next
    INDEX
    Explanations

    in stock

    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
     cof
    -0.08
    協
    -0.07
     kể
    -0.07
    .SQL
    -0.07
     coer
    -0.07
    뉴스
    -0.07
     watered
    -0.07
    ಕರ್ತ
    -0.07
    oan
    -0.07
    acula
    -0.07
    POSITIVE LOGITS
     voorraad
    0.12
     stok
    0.10
     товара
    0.10
    库存
    0.09
     ọja
    0.09
     availability
    0.09
     অবস্থ
    0.09
    商品
    0.08
     verkrijgbaar
    0.08
    Item
    0.08
    Activations Density 0.033%

    No Known Activations