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. 49137
    Prev
    Next
    INDEX
    Explanations

    US presidents

    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
     SYN
    -0.08
    .syn
    -0.08
    _syn
    -0.08
     decal
    -0.08
    _SYN
    -0.08
     lifetime
    -0.07
    альної
    -0.07
     dê
    -0.07
     stigma
    -0.07
    RIA
    -0.07
    POSITIVE LOGITS
     palace
    0.10
     대통령
    0.09
     emperor
    0.09
     speeches
    0.09
     assassination
    0.09
     Netanyahu
    0.09
     royal
    0.09
     मंत्री
    0.09
     kerajaan
    0.09
    皇
    0.09
    Activations Density 0.100%

    No Known Activations