© 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. 45793
    Prev
    Next
    INDEX
    Explanations

    power

    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
     ouvrage
    -0.08
    mdl
    -0.08
     plaque
    -0.07
     zig
    -0.07
     yad
    -0.07
     Alm
    -0.07
    _fu
    -0.07
    Gir
    -0.07
    831
    -0.07
     wau
    -0.07
    POSITIVE LOGITS
    เต็ม
    0.09
     Nina
    0.09
    ระดับ
    0.09
     levels
    0.08
     collaborate
    0.08
    ഷ്യ
    0.08
    	T
    0.08
     रखते
    0.08
     adlı
    0.08
     सफलता
    0.08
    Activations Density 0.003%

    No Known Activations