© 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. 99206
    Prev
    Next
    INDEX
    Explanations

    long, important story

    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
     оборудования
    -0.08
     accompan
    -0.08
     isolation
    -0.08
    ge
    -0.08
     glad
    -0.08
    -shot
    -0.07
     shiny
    -0.07
     substrates
    -0.07
     aprendido
    -0.07
     dishwasher
    -0.07
    POSITIVE LOGITS
     sprawling
    0.12
     trilogy
    0.10
     finale
    0.10
     saga
    0.10
     grandeur
    0.09
     umfang
    0.09
     monumental
    0.09
    -Serie
    0.09
     terminar
    0.09
     epo
    0.09
    Activations Density 0.050%

    No Known Activations