© 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. 99432
    Prev
    Next
    INDEX
    Explanations

    Parentheses/code

    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
    -0.07
    认证
    -0.07
    会员
    -0.07
    క
    -0.07
     Olive
    -0.07
     Христ
    -0.07
     корот
    -0.07
     olive
    -0.06
     선택
    -0.06
    调
    -0.06
    POSITIVE LOGITS
    "This
    0.08
     SZ
    0.08
    "We
    0.08
    mz
    0.08
    "(
    0.08
     Zag
    0.07
    SZ
    0.07
    "The
    0.07
     "{$
    0.07
     "=
    0.07
    Activations Density 0.036%
    No Known Activations