© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 45376
    Prev
    Next
    INDEX
    Explanations

    mixture concentrations

    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
    estyle
    -0.09
     즐
    -0.08
    메
    -0.08
    aby
    -0.08
     디자인
    -0.08
    냥
    -0.07
     rhythmic
    -0.07
    imaa
    -0.07
     스타일
    -0.07
     rhyth
    -0.07
    POSITIVE LOGITS
     numerator
    0.09
     dried
    0.09
     liters
    0.09
     grams
    0.08
     ovens
    0.08
    .amount
    0.08
    、水
    0.08
     ماء
    0.08
     vlucht
    0.08
    elag
    0.08
    Activations Density 0.027%

    No Known Activations