Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 95096
    Prev
    Next
    INDEX
    Explanations

    conflict and politics

    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
    �
    -0.07
     presentation
    -0.07
     subtraction
    -0.07
     proximal
    -0.07
     openings
    -0.07
     total
    -0.06
     cintur
    -0.06
     zit
    -0.06
     equipment
    -0.06
     "]
    -0.06
    POSITIVE LOGITS
     дорого
    0.09
     قضية
    0.09
    $msg
    0.08
     تواجه
    0.08
    heap
    0.08
     разв
    0.08
    ancell
    0.08
    (resolve
    0.08
     накоп
    0.08
    ».↵↵
    0.08
    Activations Density 0.153%

    No Known Activations