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. 15-RESID-POST-AA
    6. 19320
    Prev
    Next
    INDEX
    Explanations

    13

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     واقعی
    -0.09
    rological
    -0.09
     THEY
    -0.08
     príncipe
    -0.08
    Mandatory
    -0.08
     intégrer
    -0.08
    mael
    -0.08
     compelled
    -0.08
    所谓
    -0.08
    bley
    -0.08
    POSITIVE LOGITS
     pet
    0.09
     FM
    0.08
     oatmeal
    0.08
     mugs
    0.07
    ®
    0.07
     LM
    0.07
     countertops
    0.07
     ovens
    0.07
     sidewalks
    0.07
    like
    0.07
    Activations Density 0.009%

    No Known Activations