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. 58773
    Prev
    Next
    INDEX
    Explanations

    travel safety

    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
    .offset
    -0.08
    .photo
    -0.08
    judge
    -0.07
    মূল
    -0.07
    저
    -0.07
    oster
    -0.07
     kred
    -0.07
     rewind
    -0.07
    fat
    -0.07
    hausen
    -0.07
    POSITIVE LOGITS
     violence
    0.13
     സുരക്ഷ
    0.12
     নিরাপ
    0.12
     sécur
    0.12
    安全
    0.12
     sécurité
    0.11
     безопасности
    0.11
     insecurity
    0.11
     الأمنية
    0.11
     امنیت
    0.11
    Activations Density 0.048%

    No Known Activations