Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43881
    Prev
    Next
    INDEX
    Explanations

    Message

    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
     tours
    -0.09
     partnering
    -0.08
    handlung
    -0.08
    -tour
    -0.08
     touring
    -0.08
    keurig
    -0.08
    escaped
    -0.08
    Escape
    -0.08
    segunda
    -0.08
    ोधित
    -0.08
    POSITIVE LOGITS
     inflater
    0.08
     tace
    0.08
    .dispatch
    0.07
     yin
    0.07
     unfavorable
    0.07
     favore
    0.07
     Monitor
    0.07
     impe
    0.07
    ünü
    0.07
    	dispatch
    0.07
    Activations Density 0.001%

    No Known Activations