© 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. 15-RESID-POST-AA
    11. 16423
    Prev
    Next
    INDEX
    Explanations

    math problems

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     любые
    -0.09
     любое
    -0.08
    roring
    -0.08
    уын
    -0.08
     cualquier
    -0.08
    илось
    -0.08
     вмеш
    -0.08
    овер
    -0.07
     doute
    -0.07
     противоп
    -0.07
    POSITIVE LOGITS
     somehow
    0.10
     carefully
    0.08
     nevertheless
    0.08
    -----
    0.08
     still
    0.07
     meticulously
    0.07
     isi
    0.07
    <\/
    0.07
    &);↵
    0.07
     nonetheless
    0.07
    Activations Density 0.018%

    No Known Activations