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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 71186
    Prev
    Next
    INDEX
    Explanations

    temperature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Plot
    -0.08
     выг
    -0.08
    snd
    -0.08
     Participation
    -0.07
    fly
    -0.07
     tradi
    -0.07
     सहभाग
    -0.07
     投
    -0.07
    投
    -0.07
    -pay
    -0.07
    POSITIVE LOGITS
    elsius
    0.12
     ताप
    0.12
     temperatures
    0.12
    °C
    0.12
     temperatura
    0.11
     température
    0.11
     температуры
    0.11
     temperature
    0.11
     nhiệt
    0.11
     температура
    0.11
    Activations Density 0.015%

    No Known Activations