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. 112228
    Prev
    Next
    INDEX
    Explanations

    owski

    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
     Nus
    -0.08
    .Ac
    -0.08
    ارد
    -0.07
     Rev
    -0.07
     Ac
    -0.07
    Ac
    -0.07
    ಚ್
    -0.07
    말
    -0.07
     ac
    -0.07
    نام
    -0.07
    POSITIVE LOGITS
     Mink
    0.11
     convex
    0.10
     frontera
    0.09
     clo
    0.08
     முன்ன
    0.08
    ritt
    0.08
    obl
    0.08
    _dst
    0.08
    vore
    0.07
     ảnh
    0.07
    Activations Density 0.001%

    No Known Activations