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. 15-RESID-POST-AA
    6. 19532
    Prev
    Next
    INDEX
    Explanations

    words like offer

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikipédia
    -0.08
     conformément
    -0.07
     Wikip
    -0.07
     Wiss
    -0.07
     nationales
    -0.07
     Wikipedia
    -0.07
     внес
    -0.07
     принято
    -0.07
     Wikimedia
    -0.07
     ঘটে
    -0.07
    POSITIVE LOGITS
     offerings
    0.17
     erbjud
    0.17
     angeboten
    0.17
     enticing
    0.16
    awarkan
    0.16
     ofrec
    0.16
    angebote
    0.16
     Angebote
    0.16
     menawarkan
    0.16
     anbieten
    0.15
    Activations Density 0.276%

    No Known Activations