© 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. 79121
    Prev
    Next
    INDEX
    Explanations

    чем

    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
     Cus
    -0.08
     му
    -0.08
    99
    -0.07
    Oh
    -0.07
    Apollo
    -0.07
     portions
    -0.07
     zatr
    -0.07
    (flat
    -0.07
    _union
    -0.07
     Федера
    -0.07
    POSITIVE LOGITS
     you'd
    0.08
    sob
    0.08
     she'd
    0.08
    ède
    0.07
     manche
    0.07
     studios
    0.07
    七
    0.07
     sellers
    0.07
     Sellers
    0.07
     Matters
    0.07
    Activations Density 0.010%

    No Known Activations