© 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. 91588
    Prev
    Next
    INDEX
    Explanations

    HTML table tags

    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
    avoir
    -0.08
     εξα
    -0.07
     artesanal
    -0.07
     seemingly
    -0.07
     atos
    -0.07
     Lage
    -0.07
     chore
    -0.07
     maroc
    -0.07
     sempre
    -0.07
     Französ
    -0.07
    POSITIVE LOGITS
     duidelijk
    0.09
     headers
    0.09
     headings
    0.08
    资本
    0.08
     capital
    0.08
    栏
    0.08
    _stock
    0.08
     uppercase
    0.08
    COLUMN
    0.08
    =headers
    0.08
    Activations Density 0.006%

    No Known Activations