© 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. 23-RESID-POST-AA
    11. 5604
    Prev
    Next
    INDEX
    Explanations

    O

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     horizon
    -0.07
    ों
    -0.07
     detection
    -0.07
    ाठ
    -0.07
    ili
    -0.07
     garage
    -0.07
    ाउन
    -0.07
    -R
    -0.07
     Eg
    -0.06
    zí
    -0.06
    POSITIVE LOGITS
     cheia
    0.09
    SError
    0.08
    0.08
     гри
    0.08
     tid
    0.08
     гриб
    0.08
     Islanders
    0.08
    zeć
    0.08
    ЕС
    0.08
     tam
    0.08
    Activations Density 0.000%
    No Known Activations