© 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. 505
    Prev
    Next
    INDEX
    Explanations

    debugging and logging

    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
    нулся
    -0.08
     reacting
    -0.08
     reactive
    -0.08
    ಿಶ
    -0.08
     гостини
    -0.08
     вок
    -0.08
     remet
    -0.07
    Passive
    -0.07
     passive
    -0.07
     gastron
    -0.07
    POSITIVE LOGITS
     تفاصيل
    0.09
    详细
    0.09
    .details
    0.09
     dokład
    0.09
    -details
    0.09
     Details
    0.09
     détails
    0.09
     bereits
    0.09
    -detail
    0.09
    詳細
    0.09
    Activations Density 0.003%

    No Known Activations