© 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. 48697
    Prev
    Next
    INDEX
    Explanations

    落

    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
    ğer
    -0.09
    avr
    -0.08
     �
    -0.08
     aggravated
    -0.08
     同
    -0.07
    män
    -0.07
     aggrav
    -0.07
    ondere
    -0.07
     만큼
    -0.07
     oleh
    -0.07
    POSITIVE LOGITS
    地
    0.18
    地域
    0.12
    脚
    0.12
     地
    0.11
    笔
    0.10
    袋
    0.10
    腳
    0.10
    子的
    0.10
    地产
    0.10
    子
    0.10
    Activations Density 0.001%

    No Known Activations