© 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. 30757
    Prev
    Next
    INDEX
    Explanations

    st

    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
    .same
    -0.08
     Ann
    -0.07
    (sorted
    -0.07
     Panel
    -0.07
     �
    -0.07
     Alameda
    -0.07
     Through
    -0.07
     Ladies
    -0.07
     thanh
    -0.07
     Як
    -0.07
    POSITIVE LOGITS
    unka
    0.09
    Historical
    0.09
     century
    0.09
     છેલ્લા
    0.08
     folkl
    0.08
    обрет
    0.08
     historical
    0.08
     historischen
    0.08
    -century
    0.08
     Jahrhund
    0.08
    Activations Density 0.002%

    No Known Activations