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. 53795
    Prev
    Next
    INDEX
    Explanations

    substantive suffixes

    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
    utter
    -0.07
    蒙
    -0.07
    Js
    -0.07
     moda
    -0.07
     ouvrir
    -0.07
    овав
    -0.07
    ’ouverture
    -0.07
     měli
    -0.07
    DIY
    -0.07
     hierv
    -0.07
    POSITIVE LOGITS
     substantive
    0.10
    act
    0.08
     printer
    0.07
     thigh
    0.07
    Triple
    0.07
     Zlat
    0.07
     statue
    0.07
     Impl
    0.07
     Westminster
    0.07
     statute
    0.07
    Activations Density 0.003%

    No Known Activations