© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7525
    Prev
    Next
    INDEX
    Explanations

    die

    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
     konk
    -0.08
     Oli
    -0.08
     eligible
    -0.08
     Rigidbody
    -0.07
     Visualization
    -0.07
     Jh
    -0.07
     wn
    -0.07
     foment
    -0.07
     Berm
    -0.07
     sly
    -0.07
    POSITIVE LOGITS
    Kun
    0.09
    坐
    0.08
    iday
    0.07
    حص
    0.07
    Fall
    0.07
     आध
    0.07
     mellitus
    0.07
    تص
    0.07
    ishing
    0.07
    pose
    0.07
    Activations Density 0.012%

    No Known Activations