© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 68436
    Prev
    Next
    INDEX
    Explanations

    chess problems involving piece placement

    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
    assoc
    -0.08
    ындағы
    -0.08
     Zahlungsm
    -0.08
     afd
    -0.08
     orale
    -0.08
    👉
    -0.08
     conduit
    -0.08
     Hardcover
    -0.08
    cookies
    -0.08
    .async
    -0.08
    POSITIVE LOGITS
     placements
    0.14
    Placement
    0.14
     placement
    0.13
     placed
    0.13
     Placement
    0.13
     размещ
    0.11
    Placed
    0.11
     yerləş
    0.10
     placé
    0.10
     placing
    0.10
    Activations Density 0.016%

    No Known Activations