© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8159
    Prev
    Next
    INDEX
    Explanations

    Fermat's Last Theorem

    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
     Pflanzen
    -0.08
     zapos
    -0.08
     essenciais
    -0.08
     synchronous
    -0.08
     plantas
    -0.08
    mousemove
    -0.08
     parlamentar
    -0.08
     teatral
    -0.08
     sustainable
    -0.07
     पौ
    -0.07
    POSITIVE LOGITS
     Jonah
    0.09
     破解
    0.08
     Nov
    0.08
    .nz
    0.08
     enormously
    0.08
     Jaipur
    0.08
     Entire
    0.08
    angkan
    0.07
    ASF
    0.07
     Mighty
    0.07
    Activations Density 0.002%

    No Known Activations