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. 102601
    Prev
    Next
    INDEX
    Explanations

    Common short words/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
     диплом
    -0.08
     Memor
    -0.08
     goalie
    -0.07
     lcd
    -0.07
    佩
    -0.07
    ynthesize
    -0.07
    ainter
    -0.07
     ICE
    -0.07
     උප
    -0.07
    .basename
    -0.07
    POSITIVE LOGITS
     בישראל
    0.16
    德国
    0.16
     Australian
    0.16
     countries
    0.16
     Australia
    0.16
     Germany
    0.15
    澳
    0.15
     Türkiye
    0.15
     Australia's
    0.15
    欧洲
    0.15
    Activations Density 0.381%

    No Known Activations