© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18393
    Prev
    Next
    INDEX
    Explanations

    customer interaction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enseñanza
    -0.09
    教学
    -0.08
    ثال
    -0.08
    طني
    -0.08
    教师
    -0.08
     generell
    -0.08
     Teachers
    -0.08
    本科
    -0.08
    ماية
    -0.08
    霞
    -0.07
    POSITIVE LOGITS
     inbox
    0.13
     고객
    0.12
     customer's
    0.12
     conversaciones
    0.11
     conversación
    0.11
     nurture
    0.11
    Interaction
    0.11
     conversations
    0.11
     العميل
    0.11
     relacionamento
    0.11
    Activations Density 0.021%

    No Known Activations