© 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. 108770
    Prev
    Next
    INDEX
    Explanations

    Motivation (Daniel Pink)

    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
    مان
    -0.07
    uerda
    -0.07
    .cljs
    -0.07
    ircuit
    -0.07
    ews
    -0.07
    ierte
    -0.07
     Journ
    -0.07
     doorway
    -0.07
    smål
    -0.07
    index
    -0.07
    POSITIVE LOGITS
    097
    0.08
     obviamente
    0.08
     gurl
    0.08
     centimeter
    0.08
     Loe
    0.08
    0.08
     kaba
    0.08
     iv
    0.08
     okun
    0.08
     benefício
    0.07
    Activations Density 0.000%

    No Known Activations