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. 113954
    Prev
    Next
    INDEX
    Explanations

    切

    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
     curios
    -0.10
     mysteries
    -0.09
     motivations
    -0.08
    òs
    -0.08
     mystery
    -0.08
     obsession
    -0.08
     squares
    -0.08
     ஆர
    -0.08
     motives
    -0.08
     муч
    -0.08
    POSITIVE LOGITS
     rebuilt
    0.10
     resilient
    0.09
     bypass
    0.09
    .restore
    0.08
     seamlessly
    0.08
    .swap
    0.08
     rebuilding
    0.08
    restore
    0.08
    Load
    0.08
    重新
    0.08
    Activations Density 0.010%

    No Known Activations