© 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. 15-RESID-POST-AA
    11. 16678
    Prev
    Next
    INDEX
    Explanations

    "twice" or "double"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    基
    -0.07
    igation
    -0.07
    -0.07
    ={
    -0.07
     conditions
    -0.07
    ="
    -0.07
    ='
    -0.07
    utho
    -0.07
     conditional
    -0.07
    рун
    -0.07
    POSITIVE LOGITS
     zweimal
    0.17
     twice
    0.15
     Twice
    0.14
     doble
    0.13
     counted
    0.13
     দ্ব
    0.13
     doubled
    0.13
     двой
    0.13
     dopp
    0.12
     mehrfach
    0.12
    Activations Density 0.011%
    No Known Activations