© 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. 65434
    Prev
    Next
    INDEX
    Explanations

    Barriers

    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
     Tab
    -0.08
     bergen
    -0.08
    ög
    -0.07
    -gener
    -0.07
    Tab
    -0.07
    icht
    -0.07
    還
    -0.07
    .visual
    -0.07
     Modal
    -0.07
     blockbuster
    -0.07
    POSITIVE LOGITS
     Lina
    0.08
    rero
    0.08
     vana
    0.08
    ODO
    0.08
     পাব
    0.08
    附近
    0.08
     lenei
    0.08
     sociedades
    0.08
    VAR
    0.08
    怎么办
    0.08
    Activations Density 0.009%

    No Known Activations