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. 109832
    Prev
    Next
    INDEX
    Explanations

    comparison

    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
    stehen
    -0.08
    steht
    -0.07
    Aw
    -0.07
     ánimo
    -0.07
    stände
    -0.07
     tilgang
    -0.07
    主体
    -0.07
    Bl
    -0.07
    staand
    -0.07
    neemt
    -0.07
    POSITIVE LOGITS
     comparisons
    0.10
     Compar
    0.10
     comparing
    0.10
     Comparing
    0.10
     Analog
    0.09
     срав
    0.09
     comparison
    0.09
     аналог
    0.09
     comparaison
    0.09
     analog
    0.09
    Activations Density 0.025%

    No Known Activations