© 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. 77914
    Prev
    Next
    INDEX
    Explanations

    meant/mean

    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
     Cater
    -0.07
    一致
    -0.07
    جيل
    -0.07
     cran
    -0.07
     extrema
    -0.07
    _cons
    -0.07
    trab
    -0.07
     justified
    -0.07
     Idee
    -0.07
    +(
    -0.07
    POSITIVE LOGITS
     UAE
    0.08
     mend
    0.08
     CIM
    0.08
     čl
    0.08
    gaard
    0.07
     YM
    0.07
     Presidency
    0.07
    efs
    0.07
     distin
    0.07
     money
    0.07
    Activations Density 0.008%

    No Known Activations