© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 63814
    Prev
    Next
    INDEX
    Explanations

    ignon

    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
     mening
    -0.09
     similares
    -0.08
     hidup
    -0.08
     Ragnar
    -0.08
    ใน
    -0.07
     primjer
    -0.07
     নম
    -0.07
    	server
    -0.07
     Genetic
    -0.07
     ruthless
    -0.07
    POSITIVE LOGITS
     convex
    0.09
     halves
    0.09
     நகர
    0.09
     quartier
    0.08
     (=
    0.08
    mediate
    0.08
    旋
    0.08
     drawers
    0.08
     squares
    0.08
     inscrit
    0.08
    Activations Density 0.002%

    No Known Activations