© 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. 23-RESID-POST-AA
    11. 97498
    Prev
    Next
    INDEX
    Explanations

    Chess bishops and knights

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فراهم
    -0.08
     exceeded
    -0.08
     poole
    -0.08
     xxx
    -0.08
    contains
    -0.08
    _contains
    -0.08
     structs
    -0.08
     contém
    -0.08
     Buy
    -0.07
    IS
    -0.07
    POSITIVE LOGITS
     navigating
    0.14
     confined
    0.14
     roam
    0.13
     roaming
    0.13
     constrained
    0.13
     restricted
    0.12
     wandering
    0.12
     navigate
    0.12
     exploring
    0.12
     moving
    0.12
    Activations Density 0.038%

    No Known Activations