© 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. 64860
    Prev
    Next
    INDEX
    Explanations

    math calculations

    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
     Alloc
    -0.10
    298
    -0.08
     alloc
    -0.08
    EMPL
    -0.08
    allocated
    -0.08
     MHz
    -0.08
     विल
    -0.08
     Rams
    -0.08
    섭
    -0.07
     allocated
    -0.07
    POSITIVE LOGITS
     monot
    0.09
     monoton
    0.08
     tempting
    0.08
     fermentation
    0.08
     booklet
    0.07
     sabido
    0.07
     tej
    0.07
     thrilling
    0.07
     hike
    0.07
     leit
    0.07
    Activations Density 0.010%

    No Known Activations