© 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. 129193
    Prev
    Next
    INDEX
    Explanations

    vomiting

    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
     wastewater
    -0.08
    стати
    -0.08
    �
    -0.07
     Training
    -0.07
     effici
    -0.07
     allow
    -0.07
     umo
    -0.07
     Waste
    -0.07
     Vancouver
    -0.07
     entr
    -0.07
    POSITIVE LOGITS
    _due
    0.09
     Sommer
    0.08
    _or
    0.08
    Larry
    0.07
     Minis
    0.07
     Bü
    0.07
    atype
    0.07
    Leb
    0.07
    agé
    0.07
     aufgrund
    0.07
    Activations Density 0.004%

    No Known Activations