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. 112080
    Prev
    Next
    INDEX
    Explanations

    tax

    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
    ීමට
    -0.08
     Verein
    -0.07
    CARE
    -0.07
    戴
    -0.07
    char
    -0.07
    ෙන
    -0.07
     worn
    -0.07
     കേ
    -0.07
    ിയ
    -0.07
     תל
    -0.07
    POSITIVE LOGITS
    subtotal
    0.09
     earnings
    0.09
     taxable
    0.09
     Ratio
    0.08
     tuyến
    0.08
    余额
    0.08
     subtotal
    0.08
     ragaz
    0.08
     Earnings
    0.08
    olella
    0.08
    Activations Density 0.010%

    No Known Activations