© 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. 11-RESID-POST-AA
    11. 827
    Prev
    Next
    INDEX
    Explanations

    Short-chain fatty acids

    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
     размещ
    -0.09
     menyer
    -0.08
     unfor
    -0.08
     сур
    -0.08
     snar
    -0.08
    dar
    -0.08
    Duplicates
    -0.08
     rugged
    -0.08
     dokon
    -0.08
    dry
    -0.08
    POSITIVE LOGITS
     inhal
    0.10
     advocate
    0.09
     advocating
    0.09
     Advocate
    0.08
     Rue
    0.08
    Rue
    0.08
    βου
    0.08
     obtainable
    0.08
    ievable
    0.08
    室
    0.08
    Activations Density 0.001%

    No Known Activations