© 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. 3-RESID-POST-AA
    11. 2693
    Prev
    Next
    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Holmes
    -0.08
     बिक
    -0.08
    ลอง
    -0.08
     Körpers
    -0.08
    ว์
    -0.07
     soggior
    -0.07
     आय
    -0.07
     postcards
    -0.07
     conversar
    -0.07
     મોટ
    -0.07
    POSITIVE LOGITS
    (Code
    0.08
     coverage
    0.08
    coverage
    0.07
    (kernel
    0.07
     sebagian
    0.07
     ene
    0.07
    (cap
    0.07
    (queue
    0.07
     competency
    0.07
     pigeon
    0.07
    Activations Density 0.001%

    No Known Activations