© 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. 97651
    Prev
    Next
    INDEX
    Explanations

    Temperature scales

    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
    orrag
    -0.08
    lications
    -0.08
     neu
    -0.08
     tailor
    -0.08
     crunch
    -0.08
     pued
    -0.07
     πλευ
    -0.07
    qubo
    -0.07
    -coated
    -0.07
    ющ
    -0.07
    POSITIVE LOGITS
     Celsius
    0.25
     Fahrenheit
    0.21
     Cel
    0.21
    Cel
    0.21
    °C
    0.20
     градусов
    0.19
     摄
    0.19
    摄
    0.19
    C
    0.18
    ℃
    0.17
    Activations Density 0.028%

    No Known Activations