© 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. 16700
    Prev
    Next
    INDEX
    Explanations

    Problem solving/reasoning

    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
     Իսկ
    -0.10
     Moreover
    -0.10
     高升
    -0.10
     金盾
    -0.10
     ოქ
    -0.10
     მაშ
    -0.09
     որն
    -0.09
     金叶
    -0.09
     易购
    -0.09
     万盛
    -0.09
    POSITIVE LOGITS
     of
    0.10
    ฯ
    0.09
     afo
    0.09
    .""
    0.09
     của
    0.09
    ;
    0.08
     andre
    0.08
    OTHER
    0.08
     they'll
    0.07
     thereof
    0.07
    Activations Density 0.356%

    No Known Activations