© 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. 31200
    Prev
    Next
    INDEX
    Explanations

    mn

    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
     spool
    -0.08
     Eindruck
    -0.08
     �
    -0.07
     ilusión
    -0.07
     hz
    -0.07
    訳
    -0.07
     verslag
    -0.07
    dv
    -0.07
     gerechnet
    -0.07
     ilus
    -0.07
    POSITIVE LOGITS
     तय
    0.12
    明确
    0.10
     claramente
    0.09
     निर्धारित
    0.09
     menentukan
    0.09
     وتص
    0.08
     تعیین
    0.08
    .define
    0.08
     ganador
    0.08
     boundaries
    0.08
    Activations Density 0.063%

    No Known Activations