© 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. 94627
    Prev
    Next
    INDEX
    Explanations

    back

    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
     sol
    -0.09
     demikian
    -0.09
     begitu
    -0.08
     Nep
    -0.08
     newcomers
    -0.07
    есп
    -0.07
    евые
    -0.07
     comprises
    -0.07
    -sol
    -0.07
     bal
    -0.07
    POSITIVE LOGITS
     إليه
    0.09
     মুহ
    0.09
     إليها
    0.08
     atrás
    0.08
     childhood
    0.08
     ilaa
    0.08
     माय
    0.08
    invest
    0.08
    trace
    0.08
     Judith
    0.08
    Activations Density 0.023%

    No Known Activations