© 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. 3-RESID-POST-AA
    11. 13039
    Prev
    Next
    INDEX
    Explanations

    ур

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HAN
    -0.08
    졌
    -0.08
     écl
    -0.07
     convo
    -0.07
     Presidency
    -0.07
     halde
    -0.07
    지고
    -0.07
     odor
    -0.07
     يعلم
    -0.07
     lightning
    -0.07
    POSITIVE LOGITS
    综合
    0.09
     הפ
    0.08
    ，从
    0.08
    746
    0.08
    	U
    0.08
     ш
    0.07
     cook
    0.07
    Separ
    0.07
    ，这
    0.07
    113
    0.07
    Activations Density 0.002%

    No Known Activations