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. 355
    Prev
    Next
    INDEX
    Explanations

    algebraic notation

    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
     maquillaje
    -0.07
     sanc
    -0.07
     segundo
    -0.07
    umes
    -0.07
     Rider
    -0.07
     التنظيم
    -0.07
     Mi
    -0.07
     تعد
    -0.07
     पत
    -0.07
     בבית
    -0.07
    POSITIVE LOGITS
     vague
    0.10
    ág
    0.07
     verbal
    0.07
     -"
    0.07
     phr
    0.07
    /math
    0.07
     wording
    0.07
     �
    0.07
     coded
    0.07
     afstand
    0.07
    Activations Density 0.126%

    No Known Activations