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. 55860
    Prev
    Next
    INDEX
    Explanations

    Green Lantern

    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
     pistes
    -0.07
    Concurrent
    -0.07
     interest
    -0.07
     ബാധ
    -0.07
    )&&
    -0.07
    ованный
    -0.07
     तरफ
    -0.07
     Informations
    -0.07
    rocks
    -0.07
     sis
    -0.07
    POSITIVE LOGITS
     Rent
    0.08
     bedraagt
    0.08
     Brom
    0.08
     czyn
    0.08
     Belediye
    0.08
     Prost
    0.08
     fauteuil
    0.08
     Savings
    0.07
     Tuition
    0.07
     betaal
    0.07
    Activations Density 0.000%

    No Known Activations