© 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. 95781
    Prev
    Next
    INDEX
    Explanations

    perfect and abundant numbers

    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
     aér
    -0.08
    turn
    -0.07
    Narr
    -0.07
    EXT
    -0.07
     maintaining
    -0.07
    oting
    -0.07
     तप
    -0.07
     gewähr
    -0.07
     narratives
    -0.07
    Maint
    -0.07
    POSITIVE LOGITS
     Foss
    0.08
     impuestos
    0.08
     Nederland
    0.07
     Uncle
    0.07
     Engelse
    0.07
     nge
    0.07
     Inglaterra
    0.07
    =sum
    0.07
     Igu
    0.07
     Lennon
    0.07
    Activations Density 0.001%

    No Known Activations