© 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. 26165
    Prev
    Next
    INDEX
    Explanations

    Tiles and dice arrangements

    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
     guarded
    -0.07
    ېرى
    -0.07
     البن
    -0.07
    帶
    -0.07
     revenir
    -0.07
    ไป
    -0.06
    达到
    -0.06
    ugut
    -0.06
    ઃ
    -0.06
     frequencies
    -0.06
    POSITIVE LOGITS
    	begin
    0.09
     protr
    0.09
     DISCLAIM
    0.09
     заканч
    0.09
     northeast
    0.09
     начали
    0.09
     abras
    0.09
     rowspan
    0.09
     beginnt
    0.08
     grenzen
    0.08
    Activations Density 0.029%

    No Known Activations