© 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. 1001
    Prev
    Next
    INDEX
    Explanations

    replace

    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
     phenomena
    -0.09
     roofs
    -0.08
     radar
    -0.08
     arvio
    -0.08
    igar
    -0.07
    blink
    -0.07
     attached
    -0.07
     Hover
    -0.07
     hovering
    -0.07
    _hover
    -0.07
    POSITIVE LOGITS
     SUBSTITUTE
    0.11
    .Replace
    0.10
     replac
    0.10
    替
    0.10
    _replace
    0.10
     Replacement
    0.10
    Replace
    0.10
     chữa
    0.09
    (rename
    0.09
     replacements
    0.09
    Activations Density 0.006%

    No Known Activations