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. 15-RESID-POST-AA
    6. 18820
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     однако
    -0.09
    istiche
    -0.09
    額
    -0.08
     albeit
    -0.08
     største
    -0.08
     uchel
    -0.08
     нийл
    -0.08
    UFACTUR
    -0.08
    四六
    -0.08
     solche
    -0.08
    POSITIVE LOGITS
    .seed
    0.08
    .json
    0.08
    Approval
    0.08
    approval
    0.08
     pous
    0.08
    Toast
    0.08
    snow
    0.08
     pokemon
    0.08
     pyt
    0.07
     minecraft
    0.07
    Activations Density 0.001%

    No Known Activations