© 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. 68698
    Prev
    Next
    INDEX
    Explanations

    time

    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
    ushing
    -0.09
     normalization
    -0.08
     normalized
    -0.07
    ків
    -0.07
    ushed
    -0.07
     പ്രത്യേക
    -0.07
    .dtd
    -0.07
    .stroke
    -0.07
    Normalization
    -0.07
     harm
    -0.07
    POSITIVE LOGITS
     Wohnzimmer
    0.10
     راز
    0.09
     unnoticed
    0.09
     બેઠ
    0.09
     misplaced
    0.08
     Theater
    0.08
     Reservations
    0.08
     منتصف
    0.08
    Minutes
    0.08
     ubicada
    0.08
    Activations Density 0.001%

    No Known Activations