© 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. 26158
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
    Chip
    -0.08
    chip
    -0.08
    .sequence
    -0.07
    .Sequence
    -0.07
     செய்யப்பட்ட
    -0.07
    בי
    -0.07
    .qual
    -0.07
    目录
    -0.07
     Chip
    -0.07
    apit
    -0.07
    POSITIVE LOGITS
     وحتى
    0.08
     afgest
    0.08
     Exceptions
    0.08
     Кроме
    0.08
    udover
    0.08
     نار
    0.08
     возбуж
    0.08
     satt
    0.08
     isegi
    0.07
     менее
    0.07
    Activations Density 0.093%

    No Known Activations