© 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. 129276
    Prev
    Next
    INDEX
    Explanations

    geometry/shapes area division

    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
     Bloom
    -0.08
     Glitter
    -0.08
     각각
    -0.08
     Bola
    -0.08
     catálogo
    -0.08
    Bloom
    -0.08
     תיק
    -0.07
     מזה
    -0.07
     শ্র
    -0.07
     reparación
    -0.07
    POSITIVE LOGITS
     symmetry
    0.09
     balancing
    0.09
    adaptive
    0.08
    ymmetric
    0.08
    öffnet
    0.08
     symmetrical
    0.08
     symmetric
    0.08
     transport
    0.08
    öffnung
    0.08
     median
    0.08
    Activations Density 0.021%

    No Known Activations