© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 2809
    Prev
    Next
    INDEX
    Explanations

    of

    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
     rapide
    -0.09
     aval
    -0.08
     પડશે
    -0.08
     epidem
    -0.07
     intrigue
    -0.07
    次数
    -0.07
     Sophie
    -0.07
     جو
    -0.07
     VE
    -0.07
     quickly
    -0.07
    POSITIVE LOGITS
     investing
    0.08
     내
    0.08
     investeren
    0.08
     Scott
    0.08
     Investing
    0.08
     Rotary
    0.08
     ethos
    0.07
     umuntu
    0.07
     사람이
    0.07
    .money
    0.07
    Activations Density 0.037%

    No Known Activations