© 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. 30307
    Prev
    Next
    INDEX
    Explanations

    by

    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
     koskaan
    -0.09
     описание
    -0.08
     Moh
    -0.08
     aldrig
    -0.08
     monopoly
    -0.08
     کبھی
    -0.08
    _shapes
    -0.07
     вил
    -0.07
     prijzen
    -0.07
     priser
    -0.07
    POSITIVE LOGITS
    Modulo
    0.10
     modulo
    0.10
     congr
    0.09
    选号
    0.09
     sums
    0.08
     parity
    0.08
     校
    0.08
    %B
    0.08
     Cong
    0.08
    校
    0.08
    Activations Density 0.034%

    No Known Activations