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

    Neuronpedia

    APICircuit 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. 12946
    Prev
    Next
    INDEX
    Explanations

    scale

    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
    din
    -0.08
     `<
    -0.08
     din
    -0.08
    aveled
    -0.08
     wind
    -0.07
     tern
    -0.07
    fall
    -0.07
    dot
    -0.07
    年
    -0.07
    andum
    -0.07
    POSITIVE LOGITS
    Balance
    0.10
    balance
    0.09
    .balance
    0.09
     balancing
    0.09
     balance
    0.09
    力度
    0.09
    (enable
    0.08
    _balance
    0.08
    (balance
    0.08
    	enable
    0.08
    Activations Density 0.002%

    No Known Activations