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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 78268
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    urpose
    -0.08
     البحث
    -0.08
     mencari
    -0.08
     housed
    -0.08
    _IOCTL
    -0.08
     conveniently
    -0.07
     centrales
    -0.07
    Mediator
    -0.07
    _nombre
    -0.07
    ฝ่าย
    -0.07
    POSITIVE LOGITS
     sprayed
    0.09
     spraying
    0.09
     build
    0.09
     tess
    0.08
     predicted
    0.08
     stitching
    0.08
    @Builder
    0.08
     stair
    0.08
     weld
    0.08
     layering
    0.08
    Activations Density 0.005%

    No Known Activations