© 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. 68853
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    EI
    -0.08
     DUI
    -0.07
    alla
    -0.07
     interessados
    -0.07
    Retry
    -0.07
     lleol
    -0.07
    laid
    -0.07
     culto
    -0.07
     Ewrope
    -0.07
    (ID
    -0.07
    POSITIVE LOGITS
     tangan
    0.08
    '*
    0.08
     involve
    0.07
    .beta
    0.07
     Kah
    0.07
     branca
    0.07
     Pediatrics
    0.07
     excav
    0.07
     arrangement
    0.07
     paragraphs
    0.07
    Activations Density 0.854%

    No Known Activations