© 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. 29673
    Prev
    Next
    INDEX
    Explanations

    Mathematical transformations

    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
     inclusão
    -0.08
    hejiang
    -0.08
     sailor
    -0.07
     manta
    -0.07
     limestone
    -0.07
     inclu
    -0.07
     toppings
    -0.07
     tense
    -0.07
     constituye
    -0.07
     inequality
    -0.07
    POSITIVE LOGITS
    Teleport
    0.09
     Кей
    0.09
     teleport
    0.09
     Не
    0.09
     Соф
    0.08
    .Encode
    0.08
    маты
    0.08
    kill
    0.08
     Очень
    0.08
     После
    0.08
    Activations Density 0.017%

    No Known Activations