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. 49329
    Prev
    Next
    INDEX
    Explanations

    op

    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
     lov
    -0.09
    -0.08
     evacuated
    -0.08
    atiquement
    -0.08
     slic
    -0.08
    ativement
    -0.08
     لكل
    -0.08
     لأي
    -0.08
    wic
    -0.08
     温
    -0.07
    POSITIVE LOGITS
    Payments
    0.09
     предложения
    0.08
     rhythms
    0.08
     движения
    0.08
     eben
    0.08
     спр
    0.08
     payment
    0.08
    Millis
    0.08
    Payment
    0.07
     ч
    0.07
    Activations Density 0.001%

    No Known Activations