Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 59086
    Prev
    Next
    INDEX
    Explanations

    Thermochemistry and thermodynamics

    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
     philosoph
    -0.08
    ('').
    -0.08
    .xaml
    -0.07
    Blind
    -0.07
    oyal
    -0.07
    BUM
    -0.07
    igion
    -0.07
     Prada
    -0.07
     seren
    -0.07
     Steve
    -0.07
    POSITIVE LOGITS
     energi
    0.10
     energetic
    0.08
     kcal
    0.08
     adsorption
    0.08
     энергия
    0.08
     heats
    0.08
     tons
    0.07
     uns
    0.07
     JOption
    0.07
     Mont
    0.07
    Activations Density 0.076%

    No Known Activations