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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51412
    Prev
    Next
    INDEX
    Explanations

    say "until"

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oberen
    -0.07
    üst
    -0.07
     داری
    -0.07
    cede
    -0.07
     segon
    -0.07
    roku
    -0.07
    óra
    -0.07
    agher
    -0.07
    kais
    -0.07
     yona
    -0.07
    POSITIVE LOGITS
     until
    0.80
     Until
    0.67
    until
    0.66
    Until
    0.64
     totdat
    0.62
    _until
    0.60
     hasta
    0.60
     jusqu
    0.59
    直到
    0.57
     till
    0.55
    Activations Density 0.315%

    No Known Activations