© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30410
    Prev
    Next
    INDEX
    Explanations

    consultation

    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
     yolu
    -0.08
    มั
    -0.07
    etat
    -0.07
     kaikk
    -0.07
     массив
    -0.07
     Tory
    -0.07
     unchecked
    -0.07
     skew
    -0.07
     array
    -0.07
    'all
    -0.07
    POSITIVE LOGITS
     vrijblijvend
    0.12
     상담
    0.12
     Beratung
    0.11
     gratuita
    0.11
     consultation
    0.11
     консульта
    0.11
     beraten
    0.10
     consultations
    0.10
     مجانية
    0.10
     Consultation
    0.10
    Activations Density 0.043%

    No Known Activations