© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7971
    Prev
    Next
    INDEX
    Explanations

    math formulas

    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
     konstant
    -0.08
     trimes
    -0.08
     चित्र
    -0.08
     experimentar
    -0.08
     ചിത്ര
    -0.07
     طريق
    -0.07
     backpack
    -0.07
     terdiri
    -0.07
    ající
    -0.07
     происход
    -0.07
    POSITIVE LOGITS
     Entfernung
    0.09
    -divider
    0.08
     Du
    0.08
     divisor
    0.08
     __
    0.08
     dast
    0.08
     Rad
    0.08
    _div
    0.07
     mukana
    0.07
     Edmund
    0.07
    Activations Density 0.064%

    No Known Activations