© 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. 94426
    Prev
    Next
    INDEX
    Explanations

    cooling ingredients

    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
     Nile
    -0.08
     Highest
    -0.07
    continental
    -0.07
     sind
    -0.07
    ĺ
    -0.07
    ukan
    -0.07
     sedikit
    -0.07
     tini
    -0.07
     Reinh
    -0.07
     SIS
    -0.07
    POSITIVE LOGITS
     Act
    0.08
     puis
    0.08
     mr
    0.07
     vitamins
    0.07
    aggable
    0.07
    Discard
    0.07
    )application
    0.07
    Associate
    0.07
     سپس
    0.07
     jot
    0.07
    Activations Density 0.005%

    No Known Activations