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. 58258
    Prev
    Next
    INDEX
    Explanations

    file

    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
     grâce
    -0.08
     Festa
    -0.08
     çık
    -0.07
     Brokers
    -0.07
     ви
    -0.07
    _CAP
    -0.07
     subsequently
    -0.07
     brokers
    -0.07
     Cherry
    -0.07
    National
    -0.07
    POSITIVE LOGITS
    HX
    0.09
     #"
    0.08
    讯
    0.08
     contem
    0.08
    actice
    0.08
    bb
    0.08
    ૨૦
    0.08
    真
    0.08
    蜘蛛
    0.08
     нее
    0.07
    Activations Density 0.001%

    No Known Activations