© 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. 11-RESID-POST-AA
    11. 111440
    Prev
    Next
    INDEX
    Explanations

    Kivy framework

    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
     OPT
    -0.10
     Moderna
    -0.09
     outage
    -0.09
    证券
    -0.09
     burden
    -0.09
     oracle
    -0.09
     €,
    -0.08
     Treasury
    -0.08
     Sauvignon
    -0.08
     outages
    -0.08
    POSITIVE LOGITS
    .mainloop
    0.09
    Gtk
    0.09
    .qml
    0.09
     sprites
    0.08
     pygame
    0.08
    (Sprite
    0.08
    sprite
    0.08
    (QWidget
    0.08
     rozp
    0.08
    Touchable
    0.08
    Activations Density 0.003%

    No Known Activations