© 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. 78142
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     lethal
    -0.09
    _CUSTOM
    -0.08
    _FIRST
    -0.08
    etel
    -0.08
    _READ
    -0.08
    ulik
    -0.08
     premiere
    -0.08
    _articles
    -0.08
    CUSTOM
    -0.08
    _RD
    -0.08
    POSITIVE LOGITS
     comma
    0.13
     commas
    0.13
     separated
    0.11
    -separated
    0.11
     перечис
    0.11
    列表
    0.10
    Comma
    0.10
     separados
    0.10
    comma
    0.10
     список
    0.10
    Activations Density 0.015%

    No Known Activations