© 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. 3-RESID-POST-AA
    11. 2630
    Prev
    Next
    INDEX
    Explanations

    estate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    928
    -0.07
    527
    -0.07
     toku
    -0.07
    atur
    -0.07
    536
    -0.07
     chí
    -0.07
     tiki
    -0.07
     hor
    -0.07
     respecting
    -0.07
    521
    -0.07
    POSITIVE LOGITS
     Rental
    0.09
     Estate
    0.08
     περισσότερο
    0.08
     недвижимости
    0.08
     Orbit
    0.08
     والسي
    0.08
     والج
    0.08
     vulnerable
    0.07
     }}">↵
    0.07
    ೀತಿ
    0.07
    Activations Density 0.011%

    No Known Activations