© 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. 11-RESID-POST-AA
    11. 129118
    Prev
    Next
    INDEX
    Explanations

    architecture

    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
     Emails
    -0.10
    病毒
    -0.10
     വൈറ
    -0.10
     addiction
    -0.09
     spreadsheets
    -0.09
     ransomware
    -0.09
    Fitness
    -0.09
     roommate
    -0.09
    derall
    -0.09
     produtividade
    -0.09
    POSITIVE LOGITS
     protr
    0.14
     recessed
    0.12
     decorative
    0.12
     curved
    0.12
     ornate
    0.12
     Gothic
    0.12
     crowns
    0.11
     masonry
    0.11
     bevel
    0.11
     декоратив
    0.10
    Activations Density 0.028%

    No Known Activations