© 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. 23-RESID-POST-AA
    11. 6108
    Prev
    Next
    INDEX
    Explanations

    Trou

    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
     מנת
    -0.08
    ionado
    -0.08
    meister
    -0.07
    iono
    -0.07
    .espresso
    -0.07
    яют
    -0.07
     المدار
    -0.07
    .pin
    -0.07
     Katy
    -0.07
    tie
    -0.07
    POSITIVE LOGITS
    bles
    0.15
    blem
    0.14
    ble
    0.13
    bled
    0.11
    bad
    0.11
    bling
    0.11
    블
    0.10
    Ser
    0.10
    ver
    0.10
    BLE
    0.09
    Activations Density 0.001%

    No Known Activations