© 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. 29653
    Prev
    Next
    INDEX
    Explanations

    Bob

    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
     inj
    -0.09
    fts
    -0.08
     DAT
    -0.07
     vascular
    -0.07
    yev
    -0.07
     kw
    -0.07
    pad
    -0.07
     inc
    -0.07
    ıcı
    -0.07
     versucht
    -0.07
    POSITIVE LOGITS
     Gardner
    0.08
    tum
    0.08
    童
    0.08
     Lee
    0.08
     Rams
    0.07
     दृ
    0.07
     क्लिक
    0.07
     тыш
    0.07
    -même
    0.07
    陈
    0.07
    Activations Density 0.004%

    No Known Activations