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. 18997
    Prev
    Next
    INDEX
    Explanations

    log timestamps

    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
     vorig
    -0.09
    岭
    -0.08
     Taiwan
    -0.08
    цам
    -0.08
     senare
    -0.08
     åter
    -0.08
    кам
    -0.08
     esti
    -0.08
    цом
    -0.08
    очным
    -0.08
    POSITIVE LOGITS
     adjacent
    0.07
    'assurance
    0.07
    iguiente
    0.07
    urances
    0.07
     التالية
    0.07
     accompanying
    0.07
     surrounding
    0.07
     ਨਾਲ
    0.07
     neighboring
    0.07
    jede
    0.07
    Activations Density 0.021%

    No Known Activations