© 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. 25149
    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
     Hague
    -0.08
     cuidados
    -0.08
    isela
    -0.08
     Flesh
    -0.08
    ENAME
    -0.08
    ewise
    -0.08
     Dent
    -0.08
    Informe
    -0.08
     nomes
    -0.07
    _LOCAL
    -0.07
    POSITIVE LOGITS
     tabl
    0.08
     floors
    0.08
     tricky
    0.08
     equilibrium
    0.07
     тр
    0.07
     객
    0.07
     катал
    0.07
     courtyard
    0.07
     uitgang
    0.07
    尋
    0.07
    Activations Density 0.027%

    No Known Activations