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. 60488
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     devo
    -0.08
     vira
    -0.08
     crispy
    -0.08
    Multiplier
    -0.08
    -On
    -0.08
    /mock
    -0.08
     bland
    -0.08
     særlig
    -0.08
    -on
    -0.08
    िविध
    -0.08
    POSITIVE LOGITS
    532
    0.08
    kund
    0.08
     fark
    0.08
     குட
    0.08
    кур
    0.08
     Elevated
    0.08
     indictment
    0.07
    yrics
    0.07
     ք
    0.07
    alah
    0.07
    Activations Density 0.006%

    No Known Activations