© 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. 23-RESID-POST-AA
    11. 97766
    Prev
    Next
    INDEX
    Explanations

    adding

    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
     manipulating
    -0.10
     possesses
    -0.09
     exists
    -0.09
     vollständig
    -0.08
     operates
    -0.08
     possessed
    -0.08
    izes
    -0.08
     פאל
    -0.08
     transporting
    -0.08
     ամբողջ
    -0.08
    POSITIVE LOGITS
    增加
    0.29
    加
    0.24
    加入
    0.24
    添加
    0.22
     добавить
    0.22
     добав
    0.22
     加
    0.21
    増
    0.21
     添加
    0.20
    ，加
    0.20
    Activations Density 0.056%

    No Known Activations