© 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. 70603
    Prev
    Next
    INDEX
    Explanations

    video games

    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
     Brexit
    -0.11
     trillion
    -0.11
    新能源
    -0.10
     Airbnb
    -0.10
    /swagger
    -0.10
     billionaire
    -0.10
     wellness
    -0.09
     Biden
    -0.09
    Instagram
    -0.09
     waiver
    -0.09
    POSITIVE LOGITS
     Atari
    0.14
     sprites
    0.12
     당시
    0.11
    sprites
    0.11
     Sega
    0.11
     Motorola
    0.11
     sprite
    0.11
    (sprite
    0.10
     freeware
    0.10
     Macintosh
    0.10
    Activations Density 0.043%

    No Known Activations