© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47282
    Prev
    Next
    INDEX
    Explanations

    fatty acids and vitamins

    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
    .Alert
    -0.08
     alphabetical
    -0.07
    .Note
    -0.07
     transit
    -0.07
    И
    -0.07
    оло
    -0.07
     предупреж
    -0.07
     Context
    -0.07
     foliage
    -0.07
     leaves
    -0.07
    POSITIVE LOGITS
     brutality
    0.09
     brutal
    0.09
    гр
    0.08
     Apart
    0.08
    eryl
    0.08
    ەك
    0.07
    Factories
    0.07
    ություններից
    0.07
    arest
    0.07
     Stavanger
    0.07
    Activations Density 0.002%

    No Known Activations