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. 120128
    Prev
    Next
    INDEX
    Explanations

    test, sandbox

    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
    [curr
    -0.09
     curr
    -0.09
    [cur
    -0.08
    	curr
    -0.08
    fügb
    -0.08
    (curr
    -0.08
    .Buffered
    -0.08
    urations
    -0.08
    _curr
    -0.08
    _cur
    -0.08
    POSITIVE LOGITS
    paypal
    0.09
     tips
    0.08
    帐号
    0.08
     Payment
    0.08
     payments
    0.08
    额度
    0.07
    authentication
    0.07
    pez
    0.07
     ödeme
    0.07
    Payment
    0.07
    Activations Density 0.001%

    No Known Activations