© 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. 47329
    Prev
    Next
    INDEX
    Explanations

    day

    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
    embership
    -0.09
     HOM
    -0.08
     ctl
    -0.07
     membership
    -0.07
    계를
    -0.07
     rẹ
    -0.07
     mère
    -0.07
     eka
    -0.07
     leon
    -0.07
     kings
    -0.07
    POSITIVE LOGITS
    вет
    0.09
     रंग
    0.08
     رنگ
    0.08
    )V
    0.08
    )v
    0.08
    547
    0.08
     волосы
    0.07
    用品
    0.07
     employers
    0.07
     Arbeitgeber
    0.07
    Activations Density 0.001%

    No Known Activations