© 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. 75868
    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
    .xlsx
    -0.08
    (prev
    -0.08
    惠
    -0.07
     correlations
    -0.07
    	input
    -0.07
    (Network
    -0.07
    Swift
    -0.07
    ensi
    -0.07
    _pref
    -0.07
    	switch
    -0.07
    POSITIVE LOGITS
     Locations
    0.09
     misch
    0.08
     ubic
    0.08
     LIABLE
    0.08
    位置
    0.08
    umbus
    0.08
     tus
    0.08
     trot
    0.08
     teased
    0.08
     عين
    0.08
    Activations Density 0.007%

    No Known Activations