© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49160
    Prev
    Next
    INDEX
    Explanations

    foreign text

    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
    �ვ
    -0.10
    �ნ
    -0.08
    �ლ
    -0.08
    合彩
    -0.08
    ್ಚ
    -0.08
    ikið
    -0.08
     花
    -0.08
     legalized
    -0.08
    кті
    -0.08
    (diff
    -0.08
    POSITIVE LOGITS
     imperative
    0.08
     yor
    0.07
    _way
    0.07
     functional
    0.07
    _orders
    0.07
     Capacity
    0.07
     आदेश
    0.07
     volum
    0.07
     way
    0.07
     manier
    0.06
    Activations Density 0.000%

    No Known Activations