© 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. 65345
    Prev
    Next
    INDEX
    Explanations

    text snippets

    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
     coronary
    -0.07
     relacionado
    -0.07
     round
    -0.07
     relação
    -0.07
    وفر
    -0.07
     conferir
    -0.07
    icato
    -0.07
     riguarda
    -0.07
     planejamento
    -0.07
     condições
    -0.07
    POSITIVE LOGITS
     Invisible
    0.09
     invisible
    0.08
     tucked
    0.08
     Junior
    0.08
     armies
    0.08
     Doe
    0.07
     Tal
    0.07
     Соф
    0.07
     sunsets
    0.07
    Eyes
    0.07
    Activations Density 0.104%

    No Known Activations