© 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. 26095
    Prev
    Next
    INDEX
    Explanations

    of

    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
     Vorge
    -0.08
    327
    -0.08
     baze
    -0.07
    anderen
    -0.07
    cte
    -0.07
    .analysis
    -0.07
     tendencies
    -0.07
     Clinical
    -0.07
     Evaluation
    -0.07
     assistance
    -0.07
    POSITIVE LOGITS
     색
    0.09
    陽
    0.09
     balón
    0.08
     colores
    0.08
     colors
    0.08
    Colors
    0.08
    colors
    0.08
    季
    0.08
     cámara
    0.08
     estación
    0.08
    Activations Density 0.014%

    No Known Activations