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. 49084
    Prev
    Next
    INDEX
    Explanations

    Non-English text

    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
     comment
    -0.07
     constant
    -0.07
     অত
    -0.07
     expecting
    -0.07
     receiving
    -0.07
     horses
    -0.07
     risk
    -0.07
     conversion
    -0.07
     قص
    -0.07
     symmetrical
    -0.07
    POSITIVE LOGITS
     dominance
    0.09
     footh
    0.09
     etabl
    0.09
    尊
    0.09
     etabli
    0.08
     domine
    0.08
     supremacy
    0.08
     behaupt
    0.08
     尊
    0.08
     strada
    0.08
    Activations Density 0.034%

    No Known Activations