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. 54261
    Prev
    Next
    INDEX
    Explanations

    partition

    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
     ağı
    -0.08
     Alla
    -0.07
     ilan
    -0.07
     inge
    -0.07
     Taschen
    -0.07
     aprobar
    -0.07
     kath
    -0.07
     Elo
    -0.07
     bazı
    -0.07
     interpretación
    -0.07
    POSITIVE LOGITS
     garantir
    0.10
     garantindo
    0.09
     гарант
    0.09
     guarantee
    0.09
    .Unique
    0.09
     guaranteed
    0.09
    保証
    0.09
     guaranteeing
    0.09
    .unique
    0.08
     tamanho
    0.08
    Activations Density 0.001%

    No Known Activations