© 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. 45675
    Prev
    Next
    INDEX
    Explanations

    Northern

    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
     fees
    -0.09
     저
    -0.08
     forage
    -0.08
     smartphones
    -0.08
     Grosso
    -0.08
    дых
    -0.08
     penalty
    -0.08
     असे
    -0.07
     photos
    -0.07
     frais
    -0.07
    POSITIVE LOGITS
     bipolar
    0.10
     Sarajevo
    0.10
     Bikini
    0.09
     Belfast
    0.09
     Dayton
    0.08
    PART
    0.08
     stal
    0.08
    共和
    0.08
     tear
    0.08
     civile
    0.08
    Activations Density 0.006%

    No Known Activations