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. 48985
    Prev
    Next
    INDEX
    Explanations

    file

    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
     volts
    -0.09
     fal
    -0.09
     বিজ
    -0.09
     چ
    -0.08
     spreadsheet
    -0.08
     depl
    -0.08
     bur
    -0.08
     volt
    -0.07
     πρω
    -0.07
    果
    -0.07
    POSITIVE LOGITS
    Pedido
    0.08
     судеб
    0.08
     Palazzo
    0.08
    'état
    0.07
    _DEFINED
    0.07
    ibh
    0.07
    Etat
    0.07
     Theft
    0.07
     SAE
    0.07
    _definition
    0.07
    Activations Density 0.004%

    No Known Activations