© 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. 30120
    Prev
    Next
    INDEX
    Explanations

    Geometry point of intersection

    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
     Capri
    -0.08
    echo
    -0.08
    merc
    -0.07
    เลือ
    -0.07
    UTF
    -0.07
     bottled
    -0.07
    ไม้
    -0.07
    conto
    -0.07
     bedroom
    -0.07
    merci
    -0.07
    POSITIVE LOGITS
     (?)
    0.09
     bridging
    0.08
     theres
    0.08
    73
    0.08
     bridge
    0.08
    桥
    0.08
     somewhere
    0.08
    _bridge
    0.08
    .Geometry
    0.08
     �
    0.08
    Activations Density 0.014%

    No Known Activations