Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 23306
    Prev
    Next
    INDEX
    Explanations

    dams, rivers, ecological disruption

    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
    仪
    -0.08
     saman
    -0.08
    ರಿ
    -0.08
    ,则
    -0.08
    Tapped
    -0.07
    ാങ
    -0.07
    রি
    -0.07
     yaptığı
    -0.07
    രി
    -0.07
    -0.07
    POSITIVE LOGITS
    acter
    0.08
     Kron
    0.08
     Yur
    0.08
     GMT
    0.07
     tanto
    0.07
     Ru
    0.07
     TIFF
    0.07
     voire
    0.07
     Alicante
    0.07
     insuff
    0.07
    Activations Density 0.000%

    No Known Activations