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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 31490
    Prev
    Next
    INDEX
    Explanations

    nutrition

    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
    ଙ
    -0.09
     nga
    -0.08
     হয়েছেন
    -0.08
    аҭ
    -0.07
     გარდ
    -0.07
    igning
    -0.07
     দিয়েছেন
    -0.07
    ĝis
    -0.07
    ङ
    -0.07
     Macbeth
    -0.07
    POSITIVE LOGITS
    <|endoftext|>
    0.20
    <|reserved_200016|>
    0.17
    。↵↵↵
    0.08
     TI
    0.07
     Vin
    0.07
    0.07
     sí
    0.07
    0.07
     Förder
    0.06
     Hopefully
    0.06
    Activations Density 2.158%
    No Known Activations