© 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. 75566
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    Fld
    -0.08
    orp
    -0.08
    feeds
    -0.08
     nigba
    -0.08
    版权
    -0.07
    lk
    -0.07
     Lob
    -0.07
    Phones
    -0.07
    phone
    -0.07
    lw
    -0.07
    POSITIVE LOGITS
    Observe
    0.08
     /**↵
    0.08
    팔
    0.08
     prud
    0.08
     provoke
    0.07
    (_,
    0.07
     •
    0.07
     skl
    0.07
    акон
    0.07
     ना
    0.07
    Activations Density 0.028%

    No Known Activations