© 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. 25862
    Prev
    Next
    INDEX
    Explanations

    composite decking/fencing

    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
     wavelength
    -0.08
     corp
    -0.07
    .Annotation
    -0.07
     wavelengths
    -0.07
     milliseconds
    -0.07
    .chrom
    -0.07
     PMID
    -0.07
     Corp
    -0.07
    ولوج
    -0.07
    isl
    -0.07
    POSITIVE LOGITS
     HOA
    0.12
     homeowners
    0.12
     marina
    0.10
     homeowner
    0.10
     campground
    0.10
     модер
    0.10
    Ự
    0.10
     cosmetic
    0.09
     lawn
    0.09
     mower
    0.09
    Activations Density 0.031%

    No Known Activations