© 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. 7-RESID-POST-AA
    11. 1442
    Prev
    Next
    INDEX
    Explanations

    plan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    coe
    -0.08
     reckless
    -0.08
     Zeb
    -0.08
     beers
    -0.08
    Bird
    -0.08
     Preisen
    -0.07
     Birds
    -0.07
     백
    -0.07
    Dos
    -0.07
     alphabetical
    -0.07
    POSITIVE LOGITS
    住宅
    0.10
    布局
    0.10
     planners
    0.09
     visually
    0.09
    诊
    0.09
     परिसर
    0.09
    面积
    0.08
    设计
    0.08
    划
    0.08
     accommodating
    0.08
    Activations Density 0.010%

    No Known Activations