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. 11824
    Prev
    Next
    INDEX
    Explanations

    political fragmentation

    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
    order
    -0.09
     slimming
    -0.08
     поезд
    -0.08
    순
    -0.08
    泳
    -0.07
    后台
    -0.07
    Personnel
    -0.07
    -order
    -0.07
     personnel
    -0.07
    pendicular
    -0.07
    POSITIVE LOGITS
     fragmented
    0.15
     fragmentation
    0.11
     factions
    0.11
     fragments
    0.10
     alliances
    0.10
    ,各
    0.10
    fragment
    0.10
     tribes
    0.10
     kingdoms
    0.10
     feud
    0.09
    Activations Density 0.027%

    No Known Activations