© 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. 96390
    Prev
    Next
    INDEX
    Explanations

    mass

    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
     meditation
    -0.08
     waves
    -0.08
    waves
    -0.08
    coupon
    -0.08
     coupon
    -0.08
     affair
    -0.08
    atoires
    -0.08
    زيارة
    -0.08
    -direction
    -0.08
    wave
    -0.08
    POSITIVE LOGITS
     重
    0.25
    质量
    0.24
    重
    0.24
    重量
    0.23
     mass
    0.20
     масса
    0.19
     массу
    0.19
     masses
    0.18
     массы
    0.18
    .mass
    0.18
    Activations Density 0.025%

    No Known Activations