© 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. 63323
    Prev
    Next
    INDEX
    Explanations

    faculty, 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
     ప్ల
    -0.09
     prévention
    -0.08
    స్
    -0.08
    Xml
    -0.08
     utak
    -0.08
    (Boolean
    -0.08
     சீ
    -0.08
     용
    -0.07
    464
    -0.07
    446
    -0.07
    POSITIVE LOGITS
     pedagog
    0.09
    Teaching
    0.09
     Lach
    0.08
     teaching
    0.08
     pedag
    0.08
     Teaching
    0.08
     педагог
    0.08
     Lu
    0.08
     jub
    0.08
     lecturers
    0.08
    Activations Density 0.018%

    No Known Activations