© 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. 108564
    Prev
    Next
    INDEX
    Explanations

    Counting letters in phrases

    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
     honing
    -0.08
     最近
    -0.08
    સી
    -0.08
     Masters
    -0.08
     independientes
    -0.08
    ]}</
    -0.08
    akhulu
    -0.08
     journals
    -0.08
    .Sql
    -0.08
    okoj
    -0.08
    POSITIVE LOGITS
     comprised
    0.11
    字符串
    0.11
    Length
    0.10
    Digits
    0.10
     spelled
    0.10
    Letters
    0.10
    Characters
    0.10
    tring
    0.10
    长度
    0.09
     syll
    0.09
    Activations Density 0.023%

    No Known Activations