© 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. 79052
    Prev
    Next
    INDEX
    Explanations

    graph theory

    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
    के
    -0.08
    hu
    -0.08
     सू
    -0.08
    सू
    -0.07
    िथ
    -0.07
     Aviation
    -0.07
    lun
    -0.07
     pren
    -0.07
     \'
    -0.07
     jewe
    -0.07
    POSITIVE LOGITS
     broccoli
    0.09
    roi
    0.09
     iloa
    0.08
     mayroon
    0.08
    网址
    0.08
     festival
    0.08
     þessa
    0.08
    的网址
    0.08
     wandeling
    0.08
    	Grid
    0.08
    Activations Density 0.002%

    No Known Activations