© 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. 1100
    Prev
    Next
    INDEX
    Explanations

    cultural symbols

    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
     сия
    -0.09
     révolution
    -0.09
    however
    -0.08
    procedure
    -0.08
     uburyo
    -0.08
     hesitate
    -0.08
     gelingt
    -0.08
     entèn
    -0.08
    (Constructor
    -0.08
    <Service
    -0.08
    POSITIVE LOGITS
     symbolism
    0.10
     symbolizes
    0.09
     symbolize
    0.09
     Jac
    0.09
     symbolic
    0.09
     cảnh
    0.09
     symbol
    0.08
     simbol
    0.08
     wisdom
    0.08
    /mp
    0.08
    Activations Density 0.017%

    No Known Activations