© 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. 99691
    Prev
    Next
    INDEX
    Explanations

    cloud scaling/elasticity

    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
     %=
    -0.09
     Misc
    -0.08
     travels
    -0.08
     Pflicht
    -0.08
    Misc
    -0.08
     fò
    -0.08
     eighth
    -0.07
    atorio
    -0.07
     Travels
    -0.07
     Mittwoch
    -0.07
    POSITIVE LOGITS
     ramp
    0.11
     वृद्धि
    0.11
     fluctu
    0.11
     deployment
    0.10
     workloads
    0.10
     ramps
    0.10
     responsiveness
    0.10
     scalable
    0.10
     resizing
    0.10
     allocation
    0.10
    Activations Density 0.013%

    No Known Activations