© 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. 3-RESID-POST-AA
    11. 2779
    Prev
    Next
    INDEX
    Explanations

    流

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogie
    -0.08
    -floor
    -0.08
     الإج
    -0.08
     aggrav
    -0.08
    -Par
    -0.07
     होते
    -0.07
    tong
    -0.07
     پرداخت
    -0.07
     voluntarily
    -0.07
    ules
    -0.07
    POSITIVE LOGITS
    人体
    0.08
     Gebäude
    0.07
    �
    0.07
    में
    0.07
     müsste
    0.07
     konusu
    0.07
    ا
    0.07
    اي
    0.07
     आदमी
    0.07
    Mem
    0.07
    Activations Density 0.000%

    No Known Activations