© 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. 91603
    Prev
    Next
    INDEX
    Explanations

    politics/elections/government

    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
    eco
    -0.08
    ='\
    -0.08
    aları
    -0.08
    al
    -0.08
    તી
    -0.07
    als
    -0.07
     માં
    -0.07
     konnten
    -0.07
    Parsed
    -0.07
     qor
    -0.07
    POSITIVE LOGITS
     someday
    0.09
     בעת
    0.09
    Será
    0.09
     sometime
    0.09
     скоро
    0.08
     بعد
    0.08
     serius
    0.08
     soon
    0.08
    今年
    0.08
     sooner
    0.08
    Activations Density 0.192%

    No Known Activations