© 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. 91763
    Prev
    Next
    INDEX
    Explanations

    you and thanks

    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
     appeals
    -0.08
     الب
    -0.08
     degli
    -0.07
     qil
    -0.07
     koji
    -0.07
    (repo
    -0.07
    Series
    -0.07
     kort
    -0.07
     polos
    -0.07
     przep
    -0.07
    POSITIVE LOGITS
     Insider
    0.08
    ogene
    0.08
    \web
    0.08
     odm
    0.07
     MAD
    0.07
     ANT
    0.07
    ready
    0.07
     సో
    0.07
     insider
    0.07
    rod
    0.07
    Activations Density 0.005%

    No Known Activations