© 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. 47677
    Prev
    Next
    INDEX
    Explanations

    fn

    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
     trying
    -0.08
     twisted
    -0.08
     API
    -0.07
     they're
    -0.07
     می
    -0.07
    ococcus
    -0.07
     specific
    -0.07
     tied
    -0.07
    .foundation
    -0.07
     kitchen
    -0.07
    POSITIVE LOGITS
    走势
    0.09
     NORMAL
    0.08
    Za
    0.08
    Verg
    0.08
    Comparer
    0.08
     Fahr
    0.08
    待遇
    0.08
     getopt
    0.08
    Equals
    0.08
     QRect
    0.08
    Activations Density 0.000%

    No Known Activations