© 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. 44579
    Prev
    Next
    INDEX
    Explanations

    Shipping and delivery times

    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
    dim
    -0.07
    learning
    -0.07
     entrances
    -0.07
     fading
    -0.07
    OID
    -0.07
     scav
    -0.07
     dim
    -0.07
     learning
    -0.07
    側
    -0.07
     faded
    -0.07
    POSITIVE LOGITS
    翌
    0.09
     expedite
    0.09
     ночью
    0.09
     Week
    0.09
     ઝડપી
    0.09
     expedited
    0.09
     nädal
    0.09
    overn
    0.09
     besteld
    0.08
     утром
    0.08
    Activations Density 0.041%

    No Known Activations