© 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. 30353
    Prev
    Next
    INDEX
    Explanations

    mathematical reasoning and uncertainty

    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
     Tide
    -0.08
     高
    -0.08
    ucalyptus
    -0.08
    สูง
    -0.08
    高
    -0.08
    tanggal
    -0.08
    IDA
    -0.08
    肉
    -0.08
    萝
    -0.07
    yt
    -0.07
    POSITIVE LOGITS
     excludes
    0.09
    excluded
    0.09
    Validity
    0.09
     trivial
    0.09
     ausgeschlossen
    0.08
     excluded
    0.08
     purposely
    0.08
     acknowledges
    0.08
     finit
    0.08
    Solutions
    0.08
    Activations Density 0.069%

    No Known Activations