© 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. 3-RESID-POST-AA
    6. 1129
    Prev
    Next
    INDEX
    Explanations

    that's

    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
     Davis
    -0.09
     Cox
    -0.08
    默
    -0.08
     dueño
    -0.07
    sit
    -0.07
    Phi
    -0.07
     Rost
    -0.07
     Diamond
    -0.07
     scarcity
    -0.07
    lden
    -0.07
    POSITIVE LOGITS
    vision
    0.09
    loss
    0.08
     potent
    0.07
     particulate
    0.07
     offensive
    0.07
    ています
    0.07
     stationary
    0.07
     gev
    0.07
     вид
    0.07
    ござ
    0.07
    Activations Density 0.067%

    No Known Activations