Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 102741
    Prev
    Next
    INDEX
    Explanations

    French education

    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
    _OVERRIDE
    -0.08
     Moro
    -0.07
     Cura
    -0.07
     المحت
    -0.07
    سبة
    -0.07
    swagger
    -0.07
    nb
    -0.07
    marks
    -0.07
    power
    -0.07
     denken
    -0.07
    POSITIVE LOGITS
     δε
    0.08
    ios
    0.08
     GCSE
    0.08
     vocational
    0.08
     hod
    0.08
     Residential
    0.08
    ergarten
    0.08
     ios
    0.08
    ialect
    0.08
     cp
    0.08
    Activations Density 0.008%

    No Known Activations