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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 108659
    Prev
    Next
    INDEX
    Explanations

    quadratic equations

    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
    ør
    -0.08
     overs
    -0.07
     chore
    -0.07
     ent
    -0.07
    overs
    -0.07
     Robert
    -0.07
     exceptions
    -0.07
    oul
    -0.07
     Bank
    -0.06
     Bishop
    -0.06
    POSITIVE LOGITS
    čku
    0.09
    Ix
    0.08
     tins
    0.08
    女孩
    0.08
    šku
    0.08
    :px
    0.08
     Kepala
    0.08
    Cabe
    0.08
    _IMAGES
    0.08
     crianças
    0.08
    Activations Density 0.027%

    No Known Activations