© 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. 23-RESID-POST-AA
    6. 5763
    Prev
    Next
    INDEX
    Explanations

    �

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ೀಸ್
    -0.09
    عة
    -0.08
     десят
    -0.08
     ошиб
    -0.08
     ф
    -0.08
    ીઝ
    -0.08
    .OK
    -0.08
    UREMENT
    -0.08
    ee
    -0.08
     Rö
    -0.07
    POSITIVE LOGITS
    elly
    0.09
    ileen
    0.08
    �
    0.08
    Hvis
    0.08
    awn
    0.08
     köz
    0.08
    imwe
    0.07
    ilters
    0.07
    Regression
    0.07
    illy
    0.07
    Activations Density 0.000%

    No Known Activations