© 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. 108566
    Prev
    Next
    INDEX
    Explanations

    value types in programming

    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
     ಮತ
    -0.08
    ucleotide
    -0.08
     concessions
    -0.08
     captions
    -0.08
    润
    -0.08
    ohana
    -0.08
    ürü
    -0.07
     moulin
    -0.07
     Caption
    -0.07
     teas
    -0.07
    POSITIVE LOGITS
     тип
    0.08
    इ
    0.08
    పు
    0.08
    к
    0.08
     क्ल
    0.08
    स्थान
    0.08
     데
    0.08
    -type
    0.08
     प्रकार
    0.08
    [element
    0.08
    Activations Density 0.001%

    No Known Activations