© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 64636
    Prev
    Next
    INDEX
    Explanations

    if

    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
    itekerezo
    -0.08
    aisse
    -0.08
    ereke
    -0.08
    wọ
    -0.07
     kiểm
    -0.07
    ická
    -0.07
     excellent
    -0.07
    olique
    -0.07
     Shi
    -0.07
     الرئيسي
    -0.07
    POSITIVE LOGITS
     будто
    0.09
     যেন
    0.09
     এত
    0.08
     alsof
    0.08
     inexist
    0.08
    不存在
    0.08
     utterly
    0.08
    Exist
    0.08
     nal
    0.08
    (||
    0.07
    Activations Density 0.012%

    No Known Activations