© 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. 47709
    Prev
    Next
    INDEX
    Explanations

    computer graphics/drawing

    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
     descubre
    -0.09
     crítico
    -0.08
     trata
    -0.08
     oversees
    -0.08
     emotional
    -0.08
    核心
    -0.08
     shuts
    -0.08
     phenomenal
    -0.08
     ги
    -0.08
    -0.08
    POSITIVE LOGITS
     linestyle
    0.10
     decorative
    0.09
     perpendicular
    0.09
    pendicular
    0.09
    Bezier
    0.09
     dashed
    0.09
     thicker
    0.08
     Decorative
    0.08
     DASH
    0.08
     bevel
    0.08
    Activations Density 0.004%
    No Known Activations