© 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. 91214
    Prev
    Next
    INDEX
    Explanations

    Colors and backgrounds

    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
     multiplex
    -0.09
    解析
    -0.07
    argest
    -0.07
     etiquette
    -0.07
     நூ
    -0.07
     Multip
    -0.07
     filmer
    -0.07
    tre
    -0.07
     финанс
    -0.07
     школ
    -0.07
    POSITIVE LOGITS
    .background
    0.09
    :bg
    0.09
    _BACKGROUND
    0.09
    (background
    0.09
    .Transparent
    0.08
    farbe
    0.08
    .gradient
    0.08
    background
    0.08
    	background
    0.08
    OWNER
    0.08
    Activations Density 0.009%

    No Known Activations