© 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. 19-RESID-POST-AA
    11. 103083
    Prev
    Next
    INDEX
    Explanations

    expression equation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     must
    -0.09
     harus
    -0.09
     is
    -0.08
    must
    -0.08
     are
    -0.08
    needs
    -0.08
     perlu
    -0.08
    nachts
    -0.08
     tiek
    -0.08
     adalah
    -0.08
    POSITIVE LOGITS
     involving
    0.14
     analyt
    0.12
     given
    0.11
     mathem
    0.11
     المتعلقة
    0.11
     باستخدام
    0.11
     используя
    0.11
     efficiently
    0.11
     المذك
    0.11
     accordingly
    0.11
    Activations Density 0.035%

    No Known Activations