© 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. 3-RESID-POST-AA
    11. 2935
    Prev
    Next
    INDEX
    Explanations

    han

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ಸೇರ
    -0.09
    秦
    -0.08
    ("+
    -0.08
    大发展
    -0.08
     especiais
    -0.08
     ט
    -0.08
     Voraussetzung
    -0.08
     relaxed
    -0.08
     відпов
    -0.08
    охож
    -0.07
    POSITIVE LOGITS
    ugs
    0.08
    safe
    0.08
    zig
    0.08
     YO
    0.07
    @Module
    0.07
     Yar
    0.07
    lar
    0.07
     cat
    0.07
     Ortiz
    0.07
     alert
    0.07
    Activations Density 0.001%

    No Known Activations