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. 120282
    Prev
    Next
    INDEX
    Explanations

    perfect squares

    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
     Insights
    -0.08
     wilderness
    -0.08
    Insights
    -0.08
    וו
    -0.07
     Hyper
    -0.07
     empê
    -0.07
    high
    -0.07
    perc
    -0.07
     percentual
    -0.07
     Mutual
    -0.07
    POSITIVE LOGITS
     yaitu
    0.09
     musicals
    0.08
     yakni
    0.08
     odo
    0.08
     dividido
    0.08
     teda
    0.08
     تقس
    0.08
     tedy
    0.07
     hone
    0.07
    756
    0.07
    Activations Density 0.017%

    No Known Activations