© 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. 31486
    Prev
    Next
    INDEX
    Explanations

    Focal compression

    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
     Zahlungs
    -0.08
     അംഗ
    -0.08
     jointly
    -0.08
     Zahlung
    -0.07
     ऊर्जा
    -0.07
    研发
    -0.07
     bain
    -0.07
     aner
    -0.07
     Ressourcen
    -0.07
     അഭ
    -0.07
    POSITIVE LOGITS
    偷窥
    0.10
     distortion
    0.10
     dilation
    0.09
     documentary
    0.09
     distort
    0.09
    觀看
    0.09
     thumbnails
    0.09
    isim
    0.09
    尺
    0.08
     cameo
    0.08
    Activations Density 0.007%

    No Known Activations