© 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. 11-RESID-POST-AA
    11. 25089
    Prev
    Next
    INDEX
    Explanations

    Story excerpts

    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
    	payload
    -0.08
    payload
    -0.08
    mu
    -0.08
    Med
    -0.08
    ώ
    -0.08
     Med
    -0.08
    .payload
    -0.08
     payload
    -0.07
     workshops
    -0.07
     ستكون
    -0.07
    POSITIVE LOGITS
     gaze
    0.11
     глазами
    0.11
     바라
    0.11
     captivated
    0.10
     കണ്ണ
    0.10
     చూస
    0.10
    -eyed
    0.10
     చూస్త
    0.10
    を見る
    0.10
    見る
    0.10
    Activations Density 0.054%

    No Known Activations