© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 108647
    Prev
    Next
    INDEX
    Explanations

    X-ray diffraction

    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
     creativo
    -0.09
     Operand
    -0.09
     Frog
    -0.08
     Recharge
    -0.08
     generosity
    -0.08
    _connector
    -0.08
     ಮೀ
    -0.08
    ærer
    -0.08
     Dangerous
    -0.08
    였습니다
    -0.08
    POSITIVE LOGITS
     diffraction
    0.14
     powders
    0.11
     powder
    0.11
     crystalline
    0.10
     anne
    0.10
     amor
    0.10
     crystall
    0.09
     порош
    0.09
     melting
    0.08
     zircon
    0.08
    Activations Density 0.004%

    No Known Activations