© 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. 78307
    Prev
    Next
    INDEX
    Explanations

    Events/Conventions

    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
    uchtigkeit
    -0.08
    ိတ်
    -0.07
     comprises
    -0.07
    doc
    -0.07
    纵
    -0.07
    odigo
    -0.07
    vertical
    -0.07
    �
    -0.07
    spiele
    -0.07
    Strip
    -0.07
    POSITIVE LOGITS
    jai
    0.09
     breadcrumb
    0.09
     Newspaper
    0.08
     hobby
    0.08
     TG
    0.08
    grain
    0.08
     dust
    0.08
    基金
    0.08
     fandom
    0.08
     forestry
    0.08
    Activations Density 0.013%

    No Known Activations