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. 29834
    Prev
    Next
    INDEX
    Explanations

    political interference

    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
    Chel
    -0.08
     Songs
    -0.08
    /mol
    -0.08
    mongoose
    -0.08
    ulator
    -0.08
    Songs
    -0.08
    constructor
    -0.08
     VGA
    -0.07
     prelim
    -0.07
     payable
    -0.07
    POSITIVE LOGITS
     misinformation
    0.12
     ट्विटर
    0.12
     ट्वीट
    0.11
     tweet
    0.10
     फेसबुक
    0.10
     extremist
    0.10
     tweets
    0.10
     tweeting
    0.09
     partisan
    0.09
     Ultra
    0.09
    Activations Density 0.020%

    No Known Activations