© 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. 7-RESID-POST-AA
    11. 1176
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ù
    -0.07
     Zwischen
    -0.07
    jni
    -0.07
    əy
    -0.07
     Dex
    -0.07
     FOUR
    -0.07
     넣
    -0.07
    bear
    -0.07
    ać
    -0.07
     masquer
    -0.07
    POSITIVE LOGITS
     residentes
    0.08
     Lamar
    0.08
     oer
    0.08
     teda
    0.08
     Maranh
    0.07
     mait
    0.07
    Heal
    0.07
     العاب
    0.07
     cod
    0.07
     rp
    0.07
    Activations Density 0.011%

    No Known Activations