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. 264
    Prev
    Next
    INDEX
    Explanations

    concern

    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
     �
    -0.09
     영
    -0.08
    _defined
    -0.08
    enean
    -0.07
    inars
    -0.07
     Pard
    -0.07
    TOD
    -0.07
    ذي
    -0.07
     �
    -0.07
    emaker
    -0.07
    POSITIVE LOGITS
     사항
    0.11
    사항
    0.11
    事项
    0.11
     acerca
    0.09
    เรื่อง
    0.09
     بشأن
    0.09
     चिंता
    0.08
    事項
    0.08
     serius
    0.08
     preocupación
    0.08
    Activations Density 0.026%

    No Known Activations