© 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. 11-RESID-POST-AA
    11. 78398
    Prev
    Next
    INDEX
    Explanations

    invest

    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
    咪
    -0.09
     convenc
    -0.07
     CB
    -0.07
    Mime
    -0.07
     Cricket
    -0.07
     fridge
    -0.07
     Tach
    -0.07
    rd
    -0.07
     Kampf
    -0.07
     مرور
    -0.07
    POSITIVE LOGITS
    成果
    0.09
     glitter
    0.08
    into
    0.08
     zen
    0.08
    Clicks
    0.08
     turmoil
    0.08
    Depos
    0.08
     ses
    0.08
     accrued
    0.08
     xe
    0.07
    Activations Density 0.023%

    No Known Activations