Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 53855
    Prev
    Next
    INDEX
    Explanations

    DMA and memory access

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reasoning
    -0.08
     caus
    -0.08
    etele
    -0.08
     demolished
    -0.08
     clues
    -0.07
     cues
    -0.07
     Choices
    -0.07
    embership
    -0.07
     bookstore
    -0.07
     trás
    -0.07
    POSITIVE LOGITS
     DMA
    0.14
    _DMA
    0.14
    _dma
    0.14
     dma
    0.13
    _transfer
    0.12
     transferring
    0.12
     transfer
    0.11
     Transfer
    0.11
    Transfer
    0.11
     передачи
    0.11
    Activations Density 0.005%

    No Known Activations