© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 102518
    Prev
    Next
    INDEX
    Explanations

    Amounts per unit

    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
     The
    -0.09
    �京
    -0.08
    amız
    -0.07
     Ф
    -0.07
     ਕਿ
    -0.07
     ค่า
    -0.07
    _RGCTX
    -0.07
     คู่
    -0.07
     Уз
    -0.07
    anın
    -0.07
    POSITIVE LOGITS
    Of
    0.17
    _of
    0.16
    -of
    0.16
    _OF
    0.13
     Of
    0.12
    	of
    0.12
    of
    0.11
    .of
    0.10
     мозга
    0.09
     пищи
    0.09
    Activations Density 0.135%

    No Known Activations