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. 119997
    Prev
    Next
    INDEX
    Explanations

    code

    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
     {@
    -0.10
    >{@
    -0.09
    $_['
    -0.09
    (_('
    -0.08
     moderno
    -0.08
      
    -0.08
     typical
    -0.08
    Typical
    -0.08
     adot
    -0.08
    quia
    -0.08
    POSITIVE LOGITS
    !!!!
    0.12
    Ahmed
    0.09
    llllllll
    0.09
     sasa
    0.09
    !!!!!!!!
    0.09
     !!!!!
    0.09
    ??
    0.09
    !!
    0.09
    .clicked
    0.09
     voiture
    0.09
    Activations Density 0.111%

    No Known Activations