© 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. 63936
    Prev
    Next
    INDEX
    Explanations

    Backticks and "Ex"

    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
    वर्क
    -0.08
     म्हणून
    -0.07
     stan
    -0.07
    ocks
    -0.07
     ribbons
    -0.07
    ेड
    -0.07
     разделе
    -0.07
     devise
    -0.07
    buster
    -0.07
     possessions
    -0.07
    POSITIVE LOGITS
    Insn
    0.09
    _kwargs
    0.09
    .exe
    0.09
     Levi
    0.08
     outsourcing
    0.08
     Pard
    0.08
    _Injected
    0.07
     crack
    0.07
    (TEXT
    0.07
    Args
    0.07
    Activations Density 0.018%

    No Known Activations