© 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. 15-RESID-POST-AA
    11. 16256
    Prev
    Next
    INDEX
    Explanations

    provide

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ↵↵
    -0.07
    **
    -0.07
    /or
    -0.07
    Snap
    -0.07
    одав
    -0.07
      ↵    ↵
    -0.07
      ↵↵
    -0.07
     implicitly
    -0.07
     Tack
    -0.07
    -shot
    -0.07
    POSITIVE LOGITS
     подробнее
    0.15
     подроб
    0.14
     further
    0.13
    进一步
    0.13
    详细
    0.13
     বিস্তারিত
    0.13
     detalles
    0.13
     verdere
    0.13
     details
    0.13
     Weitere
    0.12
    Activations Density 0.056%

    No Known Activations