© 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. 11-RESID-POST-AA
    6. 79396
    Prev
    Next
    INDEX
    Explanations

    mathematical pairs and combinations

    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
    -so
    -0.09
    沉
    -0.08
    IFICATE
    -0.07
    坚定
    -0.07
     延
    -0.07
    压力
    -0.07
     encarg
    -0.07
    坚持
    -0.07
    izr
    -0.07
     extended
    -0.07
    POSITIVE LOGITS
    Pairs
    0.09
    similar
    0.09
    exclude
    0.09
     homosexual
    0.09
    _pairs
    0.08
     ipairs
    0.08
     exclude
    0.08
    _duplicates
    0.08
     distinto
    0.08
    ordered
    0.08
    Activations Density 0.045%

    No Known Activations