© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 6510
    Prev
    Next
    INDEX
    Explanations

    довер

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     við
    -0.08
     iz
    -0.08
    -connected
    -0.08
     izle
    -0.08
    வி
    -0.08
    авис
    -0.08
    scala
    -0.08
     düşünd
    -0.07
     விம
    -0.07
    ishly
    -0.07
    POSITIVE LOGITS
    ие
    0.12
    ительные
    0.12
    ительными
    0.10
    ительное
    0.10
    ительных
    0.10
    ительный
    0.10
    ительным
    0.09
    ия
    0.09
    ИЕ
    0.09
    яют
    0.09
    Activations Density 0.001%

    No Known Activations