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. 112136
    Prev
    Next
    INDEX
    Explanations

    of

    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
    increments
    -0.07
     esqu
    -0.07
     complies
    -0.07
     Es
    -0.07
    planning
    -0.07
     footage
    -0.07
    Es
    -0.07
    oue
    -0.07
     Brie
    -0.07
    OMG
    -0.07
    POSITIVE LOGITS
     bordo
    0.08
    בות
    0.08
     cartoon
    0.08
     vento
    0.08
     सुझ
    0.07
     إحدى
    0.07
     encontro
    0.07
     inward
    0.07
    شرات
    0.07
     несколько
    0.07
    Activations Density 0.004%

    No Known Activations