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. 44238
    Prev
    Next
    INDEX
    Explanations

    Launch

    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
    Benef
    -0.08
     гармони
    -0.08
    έργ
    -0.08
    зывает
    -0.08
    риж
    -0.08
    μου
    -0.08
    uddy
    -0.08
    reuung
    -0.08
     Benef
    -0.08
     beneficiary
    -0.08
    POSITIVE LOGITS
    打开
    0.11
    启动
    0.11
     launch
    0.10
    .exe
    0.10
     Launcher
    0.09
     installed
    0.09
    Launcher
    0.09
     Installed
    0.08
    Launch
    0.08
     Terminal
    0.08
    Activations Density 0.021%

    No Known Activations