© 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. 54429
    Prev
    Next
    INDEX
    Explanations

    genetics and DNA

    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
     coward
    -0.10
     legs
    -0.10
     Legs
    -0.09
     stove
    -0.09
     beginner
    -0.09
    救
    -0.08
     Client
    -0.08
     Testimonials
    -0.08
     cockpit
    -0.08
     مشتری
    -0.08
    POSITIVE LOGITS
     methyl
    0.17
     phosphorylation
    0.11
     chrom
    0.11
     alterations
    0.11
     oxidative
    0.11
     hydrox
    0.10
     metabolites
    0.10
     genomic
    0.09
    染
    0.09
     transcription
    0.09
    Activations Density 0.007%

    No Known Activations