© 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. 78435
    Prev
    Next
    INDEX
    Explanations

    international and domestic law

    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
    _Left
    -0.08
    _encode
    -0.08
    ubra
    -0.08
     amenities
    -0.08
     bandwidth
    -0.07
     delay
    -0.07
     server
    -0.07
    厕所
    -0.07
    举
    -0.07
     folly
    -0.07
    POSITIVE LOGITS
     κύ
    0.09
    omar
    0.08
     overpower
    0.08
    凌
    0.08
     tercer
    0.08
     harmonie
    0.08
    INDER
    0.08
     armon
    0.08
     সিন
    0.08
    อ่าน
    0.08
    Activations Density 0.009%

    No Known Activations