© 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. 68822
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
    como
    -0.08
    ూప
    -0.07
    _thresh
    -0.07
    概
    -0.07
    Img
    -0.07
     ps
    -0.07
    -0.07
    ps
    -0.07
    _img
    -0.07
     Послед
    -0.07
    POSITIVE LOGITS
     Marin
    0.09
     مند
    0.08
     Bü
    0.08
     bambini
    0.08
     brinqu
    0.08
     Immobil
    0.08
     tritur
    0.08
     réalisée
    0.08
     Babys
    0.08
     Pierre
    0.08
    Activations Density 0.320%
    No Known Activations