© 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. 7558
    Prev
    Next
    INDEX
    Explanations

    market size

    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
    Trivia
    -0.08
    য়ার
    -0.08
     OFFICE
    -0.08
    іла
    -0.08
    .office
    -0.08
    .Office
    -0.07
    워크
    -0.07
    igher
    -0.07
    Adventure
    -0.07
    进行了
    -0.07
    POSITIVE LOGITS
     conceivable
    0.10
     feas
    0.10
     someday
    0.10
     trillion
    0.09
     envisioned
    0.09
     envis
    0.09
     envisage
    0.09
     toekomstige
    0.09
     obtainable
    0.09
     feasible
    0.09
    Activations Density 0.022%

    No Known Activations