© 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. 19-RESID-POST-AA
    11. 103634
    Prev
    Next
    INDEX
    Explanations

    Game development assets

    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
    .owner
    -0.09
    ynamodb
    -0.08
    esters
    -0.08
    <Link
    -0.08
    inerary
    -0.08
    ivariate
    -0.08
     लिंक
    -0.08
    incy
    -0.08
    trk
    -0.08
    .flink
    -0.08
    POSITIVE LOGITS
    Models
    0.14
    Scenes
    0.13
    Game
    0.13
    Textures
    0.12
    Scripts
    0.12
    Characters
    0.12
    Menus
    0.12
    Gameplay
    0.12
    Scene
    0.11
    Animals
    0.11
    Activations Density 0.002%

    No Known Activations