© 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. 7-RESID-POST-AA
    11. 1004
    Prev
    Next
    INDEX
    Explanations

    space or floating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     asymmetric
    -0.08
     первые
    -0.08
     siding
    -0.07
    har
    -0.07
     गौर
    -0.07
    astal
    -0.07
    奉
    -0.07
     taxpayers
    -0.07
    "%(
    -0.07
    uken
    -0.07
    POSITIVE LOGITS
    coffee
    0.08
    _org
    0.07
    (inner
    0.07
     forever
    0.07
     ہوں
    0.07
    ია
    0.07
    :hover
    0.07
    Interact
    0.07
    _outer
    0.07
     drank
    0.07
    Activations Density 0.001%

    No Known Activations