© 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. 19-RESID-POST-AA
    6. 103331
    Prev
    Next
    INDEX
    Explanations

    "but" in different languages

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    დღ
    -0.11
     արագ
    -0.11
     სწრაფ
    -0.11
     იყო
    -0.11
      ↵↵  ↵↵
    -0.11
     დიდი
    -0.10
    აჩნ
    -0.10
     Նրանք
    -0.10
     亿博
    -0.10
     亚洲日韩
    -0.10
    POSITIVE LOGITS
     but
    0.17
     pero
    0.15
     nhưng
    0.13
    But
    0.13
     लेकिन
    0.13
     mutta
    0.12
     aber
    0.12
    but
    0.12
     पण
    0.12
     But
    0.12
    Activations Density 0.003%

    No Known Activations