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. 43069
    Prev
    Next
    INDEX
    Explanations

    quadrilateral

    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
    สมาชิก
    -0.09
    /community
    -0.09
     excursions
    -0.09
    Animations
    -0.09
     rehears
    -0.09
    Subscriptions
    -0.08
     исполнитель
    -0.08
    /template
    -0.08
    Subscriber
    -0.08
     מנ
    -0.08
    POSITIVE LOGITS
    �
    0.08
     When
    0.08
     umb
    0.08
     clínica
    0.07
     Light
    0.07
     Bal
    0.07
     tub
    0.07
     Ratio
    0.07
     closer
    0.07
     ub
    0.07
    Activations Density 0.014%

    No Known Activations