© 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. 77948
    Prev
    Next
    INDEX
    Explanations

    Fascism

    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
     handset
    -0.08
     Silicon
    -0.08
     Weihnachts
    -0.08
    entscheidung
    -0.08
    comfort
    -0.07
     silicon
    -0.07
     школь
    -0.07
     Komfort
    -0.07
     genotype
    -0.07
     Wayne
    -0.07
    POSITIVE LOGITS
     marched
    0.09
     flutter
    0.09
     rouges
    0.08
    mixed
    0.08
     warfare
    0.08
     під
    0.08
    ्ञ
    0.08
     stiffness
    0.08
     crossed
    0.08
    战争
    0.08
    Activations Density 0.003%

    No Known Activations