© 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. 44690
    Prev
    Next
    INDEX
    Explanations

    painting

    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
    Congratulations
    -0.08
     intel
    -0.08
    ranking
    -0.07
     Qualcomm
    -0.07
     Congratulations
    -0.07
     homen
    -0.07
    Leia
    -0.07
     nicely
    -0.07
     techno
    -0.07
     ranking
    -0.07
    POSITIVE LOGITS
     peinture
    0.12
     Palette
    0.11
     paints
    0.10
     paint
    0.10
    brush
    0.10
     pintura
    0.10
     watercolor
    0.10
    Palette
    0.10
     solvents
    0.10
     dye
    0.10
    Activations Density 0.027%

    No Known Activations