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. 12294
    Prev
    Next
    INDEX
    Explanations

    code parameters

    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
     buzz
    -0.08
     viv
    -0.08
     indigenous
    -0.08
    -0.08
    ق
    -0.07
    nergy
    -0.07
    Authorities
    -0.07
     valley
    -0.07
    akke
    -0.07
    /team
    -0.07
    POSITIVE LOGITS
     customizable
    0.16
    Customization
    0.14
     customize
    0.13
     customization
    0.13
     Customize
    0.12
     옵션
    0.12
    (Optional
    0.12
     Optional
    0.12
    Customize
    0.12
     customise
    0.12
    Activations Density 0.028%

    No Known Activations