© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 114082
    Prev
    Next
    INDEX
    Explanations

    restaurant reviews

    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
     annual
    -0.08
    grunt
    -0.07
     täg
    -0.07
     Kal
    -0.07
    .daily
    -0.07
     kindergarten
    -0.07
     recurrent
    -0.07
     દ્વ
    -0.07
     highway
    -0.07
     anual
    -0.07
    POSITIVE LOGITS
     блюда
    0.11
     appetizers
    0.10
     офи
    0.10
     yemek
    0.10
     appetizer
    0.10
     platos
    0.10
     degust
    0.09
     desserts
    0.09
     pratos
    0.09
    Guests
    0.09
    Activations Density 0.057%

    No Known Activations