© 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. 108776
    Prev
    Next
    INDEX
    Explanations

    DNA/RNA coding

    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
     reposition
    -0.07
     pressure
    -0.07
     incertid
    -0.07
     সংক
    -0.07
    yy
    -0.07
     Geometry
    -0.07
     treasure
    -0.07
     contexto
    -0.07
    رج
    -0.07
    .flags
    -0.07
    POSITIVE LOGITS
    بوع
    0.08
     Buna
    0.08
     hè
    0.07
     factual
    0.07
    	th
    0.07
     கழ
    0.07
     saranno
    0.07
    accala
    0.07
    умо
    0.07
    वीं
    0.07
    Activations Density 0.001%

    No Known Activations