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. 54048
    Prev
    Next
    INDEX
    Explanations

    a

    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
     תא
    -0.08
     adopt
    -0.08
     accurately
    -0.08
     kuinka
    -0.08
     Sport
    -0.08
     adopting
    -0.08
    ogas
    -0.08
     masing
    -0.07
     nauw
    -0.07
     lukt
    -0.07
    POSITIVE LOGITS
    protected
    0.08
     Protected
    0.08
     सेट
    0.08
     provável
    0.07
     protected
    0.07
     recyclable
    0.07
    şehir
    0.07
     polite
    0.07
    Protected
    0.07
    insel
    0.07
    Activations Density 0.019%

    No Known Activations