© 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. 45341
    Prev
    Next
    INDEX
    Explanations

    dead, zombies

    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
    .FR
    -0.08
    -0.08
     прозрач
    -0.07
    (dr
    -0.07
    -Car
    -0.07
     STEP
    -0.07
    .Dat
    -0.07
     Stem
    -0.07
     proprietor
    -0.07
     Lef
    -0.07
    POSITIVE LOGITS
     secundaria
    0.08
    รก
    0.08
     ń
    0.08
    930
    0.08
     pagr
    0.08
     खान
    0.07
     forty
    0.07
     bureaucr
    0.07
    ữa
    0.07
     halda
    0.07
    Activations Density 0.000%
    No Known Activations