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. 60616
    Prev
    Next
    INDEX
    Explanations

    always

    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
     blender
    -0.08
     Chill
    -0.08
     Airbus
    -0.07
     plotted
    -0.07
    느
    -0.07
    _total
    -0.07
    arpa
    -0.07
    ashboard
    -0.07
    ternal
    -0.07
    807
    -0.07
    POSITIVE LOGITS
    以来
    0.12
     notion
    0.10
     notions
    0.09
     fascinated
    0.09
     fascination
    0.09
     था
    0.08
    -fashioned
    0.08
     ছিল
    0.07
     música
    0.07
    Been
    0.07
    Activations Density 0.043%

    No Known Activations