© 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. 97771
    Prev
    Next
    INDEX
    Explanations

    Honor of Kings

    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
     accl
    -0.09
     Kno
    -0.08
    .Act
    -0.08
     Einzahlung
    -0.08
     Fuente
    -0.08
     Ferdinand
    -0.08
     Friedrich
    -0.08
     Zutaten
    -0.08
     screwdriver
    -0.08
     huevo
    -0.07
    POSITIVE LOGITS
    Honor
    0.13
     Honor
    0.12
     honor
    0.11
     斗地主
    0.11
     Honour
    0.11
    炸金花
    0.11
     王者
    0.11
     honors
    0.10
     棋牌
    0.10
     棋牌游戏
    0.10
    Activations Density 0.003%

    No Known Activations