© 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. 64267
    Prev
    Next
    INDEX
    Explanations

    Biodiversity

    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
    额度
    -0.09
    揉
    -0.09
     "".
    -0.09
     ''.
    -0.09
     rembourse
    -0.09
     platen
    -0.09
     remboursement
    -0.08
     Minutes
    -0.08
     συνε
    -0.08
     apology
    -0.08
    POSITIVE LOGITS
     fauna
    0.21
     flora
    0.18
     biodiversity
    0.17
     biodivers
    0.16
    flora
    0.14
     especies
    0.13
     habitats
    0.12
     wildlife
    0.12
     species
    0.12
     taxa
    0.12
    Activations Density 0.060%

    No Known Activations