Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 102574
    Prev
    Next
    INDEX
    Explanations

    hematoma, surgery, medical procedures

    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
     attempts
    -0.08
     birthdays
    -0.08
     crayons
    -0.08
    021
    -0.08
     viajes
    -0.08
     productivity
    -0.08
     journeys
    -0.07
     {:.
    -0.07
     Journey
    -0.07
    ognition
    -0.07
    POSITIVE LOGITS
     הח
    0.09
     dhu
    0.08
     وسط
    0.08
     bohloko
    0.08
     منځ
    0.08
    门户
    0.08
     באזור
    0.08
     tà
    0.08
     bohlokoa
    0.08
     batho
    0.08
    Activations Density 0.007%

    No Known Activations