© 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. 68245
    Prev
    Next
    INDEX
    Explanations

    instructions and questions

    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
     шару
    -0.08
    weru
    -0.07
    cija
    -0.07
    Everybody
    -0.07
     ومح
    -0.07
     الطبيعية
    -0.07
     чест
    -0.07
     प्राकृतिक
    -0.07
    XI
    -0.07
    자로
    -0.07
    POSITIVE LOGITS
     enormous
    0.08
    "fmt
    0.07
    cedure
    0.07
     Mong
    0.07
     Session
    0.07
     vast
    0.07
     accomplish
    0.07
     tremendous
    0.07
     opdrachten
    0.07
     дальней
    0.07
    Activations Density 0.002%

    No Known Activations