© 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. 91761
    Prev
    Next
    INDEX
    Explanations

    th

    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
    Crazy
    -0.09
     Crazy
    -0.09
     Ionic
    -0.08
     nói
    -0.08
     enzymes
    -0.08
     inherited
    -0.07
    �
    -0.07
     nanos
    -0.07
     mitochond
    -0.07
     chăm
    -0.07
    POSITIVE LOGITS
     percentile
    0.18
    -percent
    0.10
    .percent
    0.10
    percent
    0.10
    percentage
    0.10
    median
    0.09
    ائري
    0.09
     Abram
    0.09
    百分
    0.09
     শতাংশ
    0.09
    Activations Density 0.014%

    No Known Activations