© 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 EvalsExportsAPI 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. 69467
    Prev
    Next
    INDEX
    Explanations

    composting

    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
     brevet
    -0.09
     Myanmar
    -0.08
     Burma
    -0.08
     CWE
    -0.08
     Monetary
    -0.08
    _MM
    -0.08
     Medical
    -0.07
     Telecommunications
    -0.07
     Pró
    -0.07
    Burst
    -0.07
    POSITIVE LOGITS
     compost
    0.15
     Compost
    0.14
     fermentation
    0.09
     sludge
    0.09
     jardin
    0.09
     fermented
    0.09
     digestion
    0.09
     déchets
    0.08
    ฮ
    0.08
     vinegar
    0.08
    Activations Density 0.009%

    No Known Activations