© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1220
    Prev
    Next
    INDEX
    Explanations

    Ukraine war

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    لوان
    -0.09
    kwal
    -0.09
    辅
    -0.08
    性能
    -0.08
    िब
    -0.08
    िभ
    -0.08
     connective
    -0.07
     Daim
    -0.07
    .Constant
    -0.07
    izante
    -0.07
    POSITIVE LOGITS
     jihad
    0.10
     Putin
    0.09
     Ukraine
    0.09
     ransomware
    0.09
     terrorist
    0.09
     ukrain
    0.09
    Ukraine
    0.08
     যুদ্ধ
    0.08
     grim
    0.08
     cartel
    0.08
    Activations Density 0.029%

    No Known Activations