© 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. 30283
    Prev
    Next
    INDEX
    Explanations

    payment for services

    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
     exploding
    -0.08
     obscene
    -0.08
     operand
    -0.08
    -ended
    -0.07
     onderdelen
    -0.07
     Operand
    -0.07
     হত
    -0.07
     समाप्त
    -0.07
     terminer
    -0.07
    Artikel
    -0.07
    POSITIVE LOGITS
     serviços
    0.09
     клап
    0.09
     обеспечение
    0.09
     regulating
    0.09
     Serviços
    0.09
    促进
    0.08
     servicios
    0.08
    生态
    0.08
     restoration
    0.08
     Services
    0.08
    Activations Density 0.007%

    No Known Activations