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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 24489
    Prev
    Next
    INDEX
    Explanations

    Multiple languages

    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
     amacı
    -0.08
     hammered
    -0.08
    cus
    -0.07
    (choice
    -0.07
    atives
    -0.07
    (Some
    -0.07
     tomonidan
    -0.07
    locals
    -0.07
     cus
    -0.07
     sanity
    -0.07
    POSITIVE LOGITS
    英文
    0.13
     영어
    0.12
     traduc
    0.11
    海外
    0.11
     abroad
    0.11
    英语
    0.11
    อังกฤษ
    0.11
    Translated
    0.11
    Translation
    0.11
    Translations
    0.10
    Activations Density 0.038%

    No Known Activations