© 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. 65489
    Prev
    Next
    INDEX
    Explanations

    Code

    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
     accommod
    -0.10
     sinc
    -0.10
     предпри
    -0.10
    quiry
    -0.09
     squeezed
    -0.08
     punct
    -0.08
     concili
    -0.08
     Wien
    -0.08
    qli
    -0.08
     vigorously
    -0.08
    POSITIVE LOGITS
     loot
    0.14
     Terraria
    0.13
     اللعبة
    0.12
    .weapon
    0.12
     Pokémon
    0.11
    .sprite
    0.11
     游戏
    0.11
    .game
    0.11
     оруж
    0.11
    Sprite
    0.11
    Activations Density 0.011%

    No Known Activations