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. 60491
    Prev
    Next
    INDEX
    Explanations

    photographs

    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
     msgs
    -0.09
     {%
    -0.08
    关注
    -0.07
     Aktionen
    -0.07
     sentimental
    -0.07
    观
    -0.07
     [`
    -0.07
     thematic
    -0.07
     ty
    -0.07
     colspan
    -0.07
    POSITIVE LOGITS
     얼굴
    0.11
    プロフィール
    0.10
     паспорт
    0.10
     biometric
    0.09
    身份证
    0.09
     selfie
    0.09
     الشخصية
    0.09
     yüz
    0.09
    写真
    0.09
    顔
    0.09
    Activations Density 0.006%

    No Known Activations