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. 15-RESID-POST-AA
    6. 19363
    Prev
    Next
    INDEX
    Explanations

    Loaded

    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
     پیر
    -0.08
     ©
    -0.07
     trast
    -0.07
     forex
    -0.07
     speziell
    -0.07
     specifically
    -0.07
     Some
    -0.07
    巴黎
    -0.07
     Pert
    -0.07
     поскольку
    -0.07
    POSITIVE LOGITS
    ægt
    0.10
    Dirty
    0.09
     swollen
    0.09
     Dirty
    0.09
     overflow
    0.09
    empt
    0.09
    arnation
    0.08
     trạng
    0.08
    ests
    0.08
     emptied
    0.08
    Activations Density 0.004%

    No Known Activations