© 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. 15-RESID-POST-AA
    6. 16702
    Prev
    Next
    INDEX
    Explanations

    multiply

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     primjer
    -0.08
     specifics
    -0.08
     особенности
    -0.08
    막
    -0.08
    tributions
    -0.07
     специф
    -0.07
    €¦↵↵
    -0.07
    vula
    -0.07
    Overlap
    -0.07
    Supports
    -0.07
    POSITIVE LOGITS
     Faktor
    0.10
     multiplying
    0.09
     Increase
    0.09
     Factor
    0.09
     oleh
    0.09
    添
    0.08
     bagi
    0.08
    ambahkan
    0.08
     בער
    0.08
     sebesar
    0.08
    Activations Density 0.012%

    No Known Activations