© 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. 26143
    Prev
    Next
    INDEX
    Explanations

    quantities

    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
     evapor
    -0.08
    iah
    -0.07
     ഒരു
    -0.07
    _async
    -0.07
    !("{
    -0.07
     Taiwan
    -0.07
    _sessions
    -0.07
     Themes
    -0.07
     {:?}",
    -0.07
     എല്ലാ
    -0.07
    POSITIVE LOGITS
    Gary
    0.08
    -uns
    0.08
    Kar
    0.08
    orten
    0.08
    Mer
    0.08
     Gary
    0.08
     fijo
    0.07
     hamm
    0.07
    ાએ
    0.07
    के
    0.07
    Activations Density 0.028%

    No Known Activations