© 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. 45792
    Prev
    Next
    INDEX
    Explanations

    equal

    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
     Astr
    -0.08
    Kind
    -0.08
    Lig
    -0.08
     contributions
    -0.08
     Lig
    -0.08
     Slot
    -0.07
     internationales
    -0.07
     Contributions
    -0.07
    Slope
    -0.07
     Tasmania
    -0.07
    POSITIVE LOGITS
    数量
    0.09
     dezelfde
    0.08
     separator
    0.08
     количеством
    0.08
     chł
    0.08
     cantidad
    0.07
     tiếp
    0.07
     prueba
    0.07
     leva
    0.07
    成立
    0.07
    Activations Density 0.008%

    No Known Activations