© 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. 15-RESID-POST-AA
    11. 16305
    Prev
    Next
    INDEX
    Explanations

    say "port"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ইত
    -0.07
    ;,
    -0.07
     অপ
    -0.07
    coon
    -0.07
    opo
    -0.07
     ABC
    -0.07
    fic
    -0.07
    ocument
    -0.07
     ident
    -0.06
     প্রকাশ
    -0.06
    POSITIVE LOGITS
     tær
    0.09
     dédiée
    0.09
    ?k
    0.08
     спортив
    0.08
     возрасте
    0.08
    款
    0.08
     قطر
    0.08
    .salary
    0.08
    .minecraft
    0.08
    .pixel
    0.08
    Activations Density 0.001%

    No Known Activations