© 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. 25249
    Prev
    Next
    INDEX
    Explanations

    Karamata's inequality

    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
     Már
    -0.08
    Ự
    -0.08
    خیص
    -0.08
    ایک
    -0.08
    Venue
    -0.08
     Boom
    -0.08
    Hace
    -0.08
     commerces
    -0.08
     Rijn
    -0.08
    gave
    -0.07
    POSITIVE LOGITS
     sorting
    0.11
    Sorting
    0.09
     SORT
    0.09
     perm
    0.09
    _sort
    0.09
     redistribution
    0.09
     sortable
    0.09
    _SORT
    0.09
     convex
    0.09
     fairness
    0.09
    Activations Density 0.007%

    No Known Activations