© 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. 7677
    Prev
    Next
    INDEX
    Explanations

    File renaming/archives

    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
    Crud
    -0.09
     indoors
    -0.09
    Lifestyle
    -0.08
    Rome
    -0.08
    Corm
    -0.08
     Crud
    -0.08
     heard
    -0.08
    来的
    -0.08
    히
    -0.08
    来到
    -0.08
    POSITIVE LOGITS
     disguised
    0.13
     disguis
    0.12
     masquer
    0.12
     disguise
    0.12
    骗局
    0.09
     pretending
    0.09
     भ्रष्ट
    0.08
     архив
    0.08
     gzip
    0.08
     डाउनलोड
    0.08
    Activations Density 0.013%

    No Known Activations