© 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. 45753
    Prev
    Next
    INDEX
    Explanations

    phosphorylation

    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
     entregar
    -0.09
     الإعلان
    -0.08
     anúncio
    -0.08
     envio
    -0.08
     Saying
    -0.08
    datum
    -0.08
     Inspire
    -0.08
    _Element
    -0.08
     اعلان
    -0.08
     عنصر
    -0.08
    POSITIVE LOGITS
     retailers
    0.08
     kin
    0.07
    ours
    0.07
     disadvantage
    0.07
     pesta
    0.07
     retail
    0.07
    .handlers
    0.07
     интенсив
    0.07
     fruct
    0.07
     stimulation
    0.07
    Activations Density 0.001%

    No Known Activations