© 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. 3-RESID-POST-AA
    11. 13299
    Prev
    Next
    INDEX
    Explanations

    Parsing structured references and abstracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     मिल
    -0.08
     économique
    -0.08
    ించడం
    -0.07
    Lessons
    -0.07
     SOS
    -0.07
     계속
    -0.07
    iral
    -0.07
    ytical
    -0.07
     사고
    -0.07
     wichtigsten
    -0.07
    POSITIVE LOGITS
     lined
    0.08
     blocks
    0.07
    _Str
    0.07
    届
    0.07
    Chang
    0.07
    。しかし
    0.07
    ライン
    0.07
     pertaining
    0.07
     undergone
    0.07
    blocks
    0.07
    Activations Density 0.000%

    No Known Activations