© 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. 131
    Prev
    Next
    INDEX
    Explanations

    All/Good

    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
     progression
    -0.09
    constraint
    -0.09
     condiciones
    -0.08
     nomination
    -0.08
     progressing
    -0.08
     avem
    -0.08
     trabalho
    -0.08
    (progress
    -0.08
    .progress
    -0.08
     reconhecimento
    -0.08
    POSITIVE LOGITS
    彻
    0.12
    掉
    0.09
    究
    0.09
    根
    0.09
    真正
    0.09
     избавиться
    0.09
    一次
    0.08
    真
    0.08
    治
    0.08
     한번
    0.08
    Activations Density 0.017%

    No Known Activations