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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23613
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
     invoices
    -0.09
    Invoices
    -0.09
    Internet
    -0.09
     errands
    -0.08
     handyman
    -0.08
     renovation
    -0.08
    \Http
    -0.08
     Internet
    -0.08
     disadvantaged
    -0.08
     disputes
    -0.08
    POSITIVE LOGITS
     sqrt
    0.11
     violating
    0.10
     elliptical
    0.10
     extrema
    0.09
     maxima
    0.09
     cos
    0.09
     maximizing
    0.08
    .Sqrt
    0.08
     montagnes
    0.08
     sinh
    0.08
    Activations Density 0.059%

    No Known Activations