© 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. 13151
    Prev
    Next
    INDEX
    Explanations

    sliding window

    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
     맡
    -0.08
    .fac
    -0.08
    *</
    -0.08
    etics
    -0.08
     실
    -0.07
     노력
    -0.07
     imbere
    -0.07
     없음
    -0.07
     спортсмен
    -0.07
     아니
    -0.07
    POSITIVE LOGITS
     contiguous
    0.10
    Sliding
    0.09
     sliding
    0.09
     viewport
    0.09
     window
    0.09
     timeframe
    0.08
    window
    0.08
     चौ
    0.08
     Window
    0.08
    -window
    0.08
    Activations Density 0.022%

    No Known Activations