© 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. 54415
    Prev
    Next
    INDEX
    Explanations

    script writing

    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
     민주
    -0.09
     demuestra
    -0.09
    dem
    -0.09
    Dem
    -0.09
    ેલી
    -0.08
    _dem
    -0.08
     democrática
    -0.08
     democracia
    -0.08
     Democracy
    -0.08
     demonstra
    -0.08
    POSITIVE LOGITS
    标题
    0.09
     concise
    0.09
     पश
    0.08
    以下
    0.08
     Asp
    0.08
     headings
    0.08
    正文
    0.08
     noirs
    0.08
    首先
    0.07
     शव
    0.07
    Activations Density 0.081%

    No Known Activations