© 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. 19-RESID-POST-AA
    11. 18809
    Prev
    Next
    INDEX
    Explanations

    Date/time formatting

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     appr
    -0.08
     Tout
    -0.07
     obst
    -0.07
     poc
    -0.07
     cmds
    -0.07
    _<?
    -0.07
     req
    -0.07
    �
    -0.07
     commands
    -0.07
     hva
    -0.07
    POSITIVE LOGITS
     nämä
    0.10
    'année
    0.09
     ಎರಡ
    0.09
     രണ്ടാം
    0.09
     обе
    0.09
    ’année
    0.08
    European
    0.08
    ‘y
    0.08
    ံ
    0.08
    Мини
    0.08
    Activations Density 0.001%

    No Known Activations