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. 30657
    Prev
    Next
    INDEX
    Explanations

    lamps and lights

    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
    .shape
    -0.09
     coloque
    -0.08
     الصغيرة
    -0.07
    地
    -0.07
     elkaar
    -0.07
    .Res
    -0.07
    Miss
    -0.07
    .Empty
    -0.07
    _RECT
    -0.07
     parques
    -0.07
    POSITIVE LOGITS
     powerful
    0.08
     TIC
    0.08
    난
    0.08
    기가
    0.08
     factory
    0.08
    ibur
    0.08
     sumber
    0.08
    -powered
    0.08
     longevity
    0.08
     sources
    0.08
    Activations Density 0.004%

    No Known Activations