© 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. 97335
    Prev
    Next
    INDEX
    Explanations

    Chinese

    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
    mme
    -0.08
    merking
    -0.08
    Compl
    -0.08
    zie
    -0.07
    plier
    -0.07
    blu
    -0.07
     padx
    -0.07
    吹
    -0.07
    ński
    -0.07
    護士
    -0.07
    POSITIVE LOGITS
    场
    0.23
    部
    0.21
    場
    0.19
    部长
    0.18
    首
    0.16
    堂
    0.16
    段
    0.15
    则
    0.15
    篇
    0.14
     部
    0.13
    Activations Density 0.015%

    No Known Activations