© 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. 54936
    Prev
    Next
    INDEX
    Explanations

    trade routes

    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
    orske
    -0.08
    780
    -0.08
     صفر
    -0.08
    950
    -0.08
    ابق
    -0.08
    78
    -0.07
    抱
    -0.07
    一家
    -0.07
    Phil
    -0.07
    	state
    -0.07
    POSITIVE LOGITS
     routes
    0.09
     corridors
    0.08
     South
    0.08
     North
    0.08
     между
    0.08
     coveted
    0.08
     देशों
    0.08
     boeken
    0.08
     маршру
    0.08
     permettant
    0.08
    Activations Density 0.015%

    No Known Activations