© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68759
    Prev
    Next
    INDEX
    Explanations

    teachers

    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
     offset
    -0.08
     location
    -0.08
     append
    -0.08
     displacement
    -0.08
     visc
    -0.08
     pallet
    -0.07
     appended
    -0.07
     SAR
    -0.07
     compensated
    -0.07
     compensation
    -0.07
    POSITIVE LOGITS
    教学
    0.18
     विद्यार्थ
    0.17
     छात्रों
    0.17
     преподав
    0.17
     pedagog
    0.16
     lecturer
    0.16
     pédagog
    0.15
     öğrenc
    0.15
     વિદ્યાર્થીઓ
    0.15
     शिक्षक
    0.15
    Activations Density 0.083%

    No Known Activations