© 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. 47719
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ులతో
    -0.08
     compliant
    -0.08
     �
    -0.07
    Rpc
    -0.07
     umgesetzt
    -0.07
    Nano
    -0.07
    Pun
    -0.07
     Medication
    -0.07
     esit
    -0.07
     mety
    -0.07
    POSITIVE LOGITS
     sister
    0.08
     clue
    0.08
     дочь
    0.08
    ыл
    0.07
     wife
    0.07
    Wo
    0.07
     sights
    0.07
     nguvu
    0.07
     friendship
    0.07
     copyright
    0.07
    Activations Density 0.004%

    No Known Activations