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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 54078
    Prev
    Next
    INDEX
    Explanations

    build

    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
     массов
    -0.08
     kleuren
    -0.08
     оттен
    -0.07
     anest
    -0.07
    ATO
    -0.07
    opped
    -0.07
    icolor
    -0.07
    nem
    -0.07
     Juríd
    -0.07
     تأتي
    -0.07
    POSITIVE LOGITS
    建设
    0.12
     xây
    0.12
    築
    0.11
     строительства
    0.11
     сооруж
    0.11
     ನಿರ್ಮ
    0.11
     구축
    0.10
    筑
    0.10
     construcción
    0.10
     construção
    0.10
    Activations Density 0.026%

    No Known Activations