© 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. 6166
    Prev
    Next
    INDEX
    Explanations

    逼

    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
    âncias
    -0.08
    ائين
    -0.08
    囲
    -0.07
    haid
    -0.07
    ls
    -0.07
    ância
    -0.07
    garan
    -0.07
     spicy
    -0.07
     compost
    -0.07
    erm
    -0.07
    POSITIVE LOGITS
    真
    0.15
    真的
    0.13
    近
    0.13
    迫
    0.12
     真
    0.11
    近平
    0.10
    格
    0.10
    真假
    0.10
    近期
    0.09
     verdade
    0.08
    Activations Density 0.002%

    No Known Activations