© 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. 99537
    Prev
    Next
    INDEX
    Explanations

    painting style

    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
    Administration
    -0.08
     تغيير
    -0.08
    кия
    -0.08
    Operation
    -0.08
     marche
    -0.07
     полез
    -0.07
     penting
    -0.07
    /types
    -0.07
     وكيف
    -0.07
     Baxter
    -0.07
    POSITIVE LOGITS
     Shar
    0.08
     artificial
    0.08
     spray
    0.08
     HDD
    0.08
     Sharp
    0.08
     overlays
    0.08
    ാൽ
    0.07
     midday
    0.07
     referencias
    0.07
     referências
    0.07
    Activations Density 0.004%

    No Known Activations