© 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. 23-RESID-POST-AA
    6. 96213
    Prev
    Next
    INDEX
    Explanations

    Chinese historical/emotional texts

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    增加
    -0.10
     important
    -0.09
     (=
    -0.09
     相
    -0.08
     =>
    -0.08
     mainly
    -0.08
    /local
    -0.08
     increase
    -0.08
     хорошие
    -0.08
    其它
    -0.08
    POSITIVE LOGITS
     relentless
    0.17
     ruthless
    0.15
    煌
    0.15
    夜夜
    0.15
     exhilarating
    0.15
     breathtaking
    0.14
     riveting
    0.14
     dazzling
    0.14
    激情
    0.13
    浩
    0.13
    Activations Density 0.056%

    No Known Activations