© 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. 23-RESID-POST-AA
    11. 97423
    Prev
    Next
    INDEX
    Explanations

    вол

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Freddie
    -0.08
     Freddy
    -0.08
    moz
    -0.08
    ZI
    -0.07
     BI
    -0.07
     jude
    -0.07
    oger
    -0.07
     Ingrid
    -0.07
     ode
    -0.07
     Cohen
    -0.07
    POSITIVE LOGITS
    ок
    0.08
    ени
    0.08
    окон
    0.08
     onmogelijk
    0.08
     губ
    0.07
    ási
    0.07
     修改
    0.07
    antsi
    0.07
     правиль
    0.07
    ãs
    0.07
    Activations Density 0.000%

    No Known Activations