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. 45020
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     grosses
    -0.08
     vět
    -0.08
     Veracruz
    -0.07
     totals
    -0.07
    ентов
    -0.07
    енты
    -0.07
    Annotated
    -0.07
     dů
    -0.07
    gross
    -0.07
    年底
    -0.07
    POSITIVE LOGITS
     funzione
    0.09
     reusable
    0.09
    Reusable
    0.09
     indefinite
    0.08
     generator
    0.08
     fungsi
    0.08
    úd
    0.08
    .function
    0.08
     infinite
    0.08
     behaving
    0.08
    Activations Density 0.005%

    No Known Activations