© 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. 3-RESID-POST-AA
    11. 13067
    Prev
    Next
    INDEX
    Explanations

    statistical significance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     đều
    -0.08
     breeders
    -0.08
     kennel
    -0.08
     breeding
    -0.07
     بشأن
    -0.07
    Creative
    -0.07
     breeder
    -0.07
    ken
    -0.07
    oming
    -0.07
     ironically
    -0.07
    POSITIVE LOGITS
     ctr
    0.09
     snel
    0.08
     crack
    0.08
     இல
    0.08
     Crack
    0.08
     Rt
    0.07
    0.07
     tahan
    0.07
     élections
    0.07
     noticias
    0.07
    Activations Density 0.000%
    No Known Activations