© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 91619
    Prev
    Next
    INDEX
    Explanations

    Bandwidth and frequency

    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
     waving
    -0.07
    .magic
    -0.07
    ('//
    -0.07
     encanta
    -0.07
     concord
    -0.07
     alternating
    -0.07
     muro
    -0.07
     привет
    -0.07
    פ
    -0.07
     mex
    -0.07
    POSITIVE LOGITS
     width
    0.13
    宽
    0.12
     bandwidth
    0.11
    width
    0.11
    	width
    0.11
    Width
    0.11
     linewidth
    0.10
    Bandwidth
    0.10
    _width
    0.10
    _DURATION
    0.10
    Activations Density 0.005%

    No Known Activations