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. 11759
    Prev
    Next
    INDEX
    Explanations

    retained earnings and equity

    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
     trafic
    -0.08
     traffic
    -0.08
     traff
    -0.08
     Traffic
    -0.08
     sprays
    -0.08
     सच
    -0.08
     brakes
    -0.08
    enteil
    -0.08
    dq
    -0.07
     frontline
    -0.07
    POSITIVE LOGITS
     accrued
    0.09
     veter
    0.09
    累计
    0.08
    Generation
    0.08
     beschlossen
    0.08
     veterans
    0.08
     choose
    0.08
     juniors
    0.07
    /issues
    0.07
     incr
    0.07
    Activations Density 0.002%

    No Known Activations