© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75443
    Prev
    Next
    INDEX
    Explanations

    recipes

    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
     duk
    -0.07
     nesta
    -0.07
     ")↵↵
    -0.07
    ୀ
    -0.07
    .Public
    -0.07
    756
    -0.07
    ூக
    -0.07
    ilie
    -0.07
     retailers
    -0.06
    ూన
    -0.06
    POSITIVE LOGITS
    兆
    0.08
     Pagan
    0.08
    ño
    0.08
    banner
    0.07
     bury
    0.07
    oteric
    0.07
    sterisk
    0.07
    gehör
    0.07
    loxacin
    0.07
    ermin
    0.07
    Activations Density 0.456%

    No Known Activations