Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 48110
    Prev
    Next
    INDEX
    Explanations

    iOS settings menus

    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
     docking
    -0.09
     docks
    -0.08
     функцион
    -0.08
    рыл
    -0.08
     любое
    -0.08
     intelect
    -0.08
    ંધ
    -0.08
    issenschaft
    -0.07
     не
    -0.07
     крат
    -0.07
    POSITIVE LOGITS
     sovereign
    0.08
     spree
    0.08
     roba
    0.08
     dismant
    0.08
     “‘
    0.08
     Prelude
    0.08
     Hors
    0.08
    folk
    0.08
    spender
    0.08
     Jens
    0.08
    Activations Density 0.005%

    No Known Activations