© 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. 3-RESID-POST-AA
    11. 903
    Prev
    Next
    INDEX
    Explanations

    Collect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gemstones
    -0.08
    keywords
    -0.08
    _duplicates
    -0.08
    136
    -0.08
    Tou
    -0.08
     Lana
    -0.07
    ldi
    -0.07
    webdriver
    -0.07
    Queens
    -0.07
    stitute
    -0.07
    POSITIVE LOGITS
    务
    0.08
     matters
    0.07
    مى
    0.07
     scrum
    0.07
     matter
    0.07
    带
    0.07
     silo
    0.07
     paper
    0.07
     wrapper
    0.07
     mas
    0.07
    Activations Density 0.006%

    No Known Activations