© 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. 19-RESID-POST-AA
    11. 102329
    Prev
    Next
    INDEX
    Explanations

    each

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iasa
    -0.09
     furthermore
    -0.08
    only
    -0.08
     が
    -0.08
    low
    -0.07
     또한
    -0.07
     அனைவர
    -0.07
     अपना
    -0.07
    aglia
    -0.07
     attaches
    -0.07
    POSITIVE LOGITS
     respective
    0.10
    机官网
    0.10
     einzelnen
    0.10
     enkele
    0.09
     jednotliv
    0.09
     группе
    0.09
    /edit
    0.09
    یتال
    0.09
    озможно
    0.09
     ομά
    0.08
    Activations Density 0.033%

    No Known Activations