© 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. 6607
    Prev
    Next
    INDEX
    Explanations

    N

    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
    ojë
    -0.09
     esse
    -0.08
     can
    -0.08
     که
    -0.08
    oj
    -0.07
     espe
    -0.07
    oa
    -0.07
     raised
    -0.07
     noticed
    -0.07
     are
    -0.07
    POSITIVE LOGITS
    мас
    0.08
    Orbit
    0.08
    Metric
    0.08
    インチ
    0.08
    Inet
    0.08
    енти
    0.08
     المهنية
    0.08
    Metrics
    0.08
    Room
    0.07
     interrog
    0.07
    Activations Density 0.000%

    No Known Activations