© 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. 43525
    Prev
    Next
    INDEX
    Explanations

    language translation and support

    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
     Elias
    -0.08
    (push
    -0.08
    .radius
    -0.08
     squared
    -0.08
    ulsion
    -0.08
    हल
    -0.07
     Bend
    -0.07
     sheriff
    -0.07
    (radius
    -0.07
     आक
    -0.07
    POSITIVE LOGITS
     Locale
    0.13
    Locale
    0.13
     langues
    0.13
     langue
    0.13
     multilingual
    0.13
    .locale
    0.13
    _locale
    0.13
     gettext
    0.12
     idiomas
    0.12
     idioma
    0.12
    Activations Density 0.035%

    No Known Activations