© 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. 44721
    Prev
    Next
    INDEX
    Explanations

    Authority actions/delegation

    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
     хийх
    -0.08
     trochu
    -0.07
    gsm
    -0.07
     Af
    -0.07
     mà
    -0.07
     தீர
    -0.07
     તે
    -0.07
     vão
    -0.07
     конечно
    -0.07
     లేద
    -0.07
    POSITIVE LOGITS
    了一
    0.08
    牧
    0.08
     JK
    0.08
     katt
    0.08
     আর
    0.07
    旗下
    0.07
     kidnapping
    0.07
     gifting
    0.07
    席
    0.07
    聘
    0.07
    Activations Density 0.172%

    No Known Activations