© 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. 69434
    Prev
    Next
    INDEX
    Explanations

    One

    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
    van
    -0.09
     HAS
    -0.08
     wash
    -0.07
     پیدا
    -0.07
     یافت
    -0.07
     leeft
    -0.07
     suma
    -0.07
     Dora
    -0.07
     पाया
    -0.07
     Handle
    -0.07
    POSITIVE LOGITS
     counseling
    0.10
     counselling
    0.09
     individually
    0.09
     терап
    0.09
     mentorship
    0.08
     mentoring
    0.08
    咨询
    0.08
     Beratung
    0.08
     Counseling
    0.08
    Individual
    0.08
    Activations Density 0.007%

    No Known Activations