© 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. 11-RESID-POST-AA
    11. 65437
    Prev
    Next
    INDEX
    Explanations

    below

    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
     законч
    -0.09
    ^{
    -0.08
    ขึ้น
    -0.08
     الن
    -0.07
     ఆ
    -0.07
    inh
    -0.07
     மத
    -0.07
    partial
    -0.07
    acters
    -0.07
     respond
    -0.07
    POSITIVE LOGITS
     вниз
    0.11
    (bottom
    0.11
     asleep
    0.10
     bottom
    0.10
     beneath
    0.10
    _BOTTOM
    0.10
     below
    0.10
     Below
    0.10
     thấp
    0.09
    底
    0.09
    Activations Density 0.091%

    No Known Activations