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. 48977
    Prev
    Next
    INDEX
    Explanations

    rule

    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
     Mea
    -0.10
     제작
    -0.09
    oglio
    -0.09
    NASA
    -0.08
     객
    -0.08
     Canva
    -0.08
    issenschaft
    -0.08
    .Supplier
    -0.08
    	Logger
    -0.08
     눈
    -0.08
    POSITIVE LOGITS
     jurisdiction
    0.11
     doctrine
    0.11
     jurisdictions
    0.11
     doctrines
    0.11
     statutes
    0.11
     constitutional
    0.10
     rules
    0.10
     statute
    0.10
     नियम
    0.10
    _rules
    0.10
    Activations Density 0.019%

    No Known Activations