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. 61004
    Prev
    Next
    INDEX
    Explanations

    customer service

    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
     Pandemic
    -0.08
     childish
    -0.08
    enson
    -0.08
     funer
    -0.08
    ocities
    -0.07
    igingen
    -0.07
    =T
    -0.07
     pandemic
    -0.07
     Tmax
    -0.07
    igkeiten
    -0.07
    POSITIVE LOGITS
    -facing
    0.10
     puas
    0.09
    权益
    0.09
    /customer
    0.09
    ambiri
    0.08
    满意
    0.08
    에게
    0.08
    *innen
    0.08
    ‍ശ
    0.08
     satisfait
    0.08
    Activations Density 0.196%

    No Known Activations