© 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. 44426
    Prev
    Next
    INDEX
    Explanations

    binary/decimal conversions

    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
     gestaltet
    -0.09
     primas
    -0.08
    /el
    -0.08
     collateral
    -0.08
     durata
    -0.08
     slurry
    -0.08
     unrealistic
    -0.08
     eterna
    -0.08
    Extr
    -0.08
     εμπ
    -0.07
    POSITIVE LOGITS
    Unsigned
    0.08
    ueble
    0.08
     jumps
    0.07
    _unsigned
    0.07
     UInt
    0.07
    ford
    0.07
     sums
    0.07
     signify
    0.07
    _UNSIGNED
    0.07
    усь
    0.07
    Activations Density 0.011%

    No Known Activations