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. 29854
    Prev
    Next
    INDEX
    Explanations

    want

    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
     गु
    -0.08
     पद
    -0.08
    macen
    -0.08
    roy
    -0.08
     खोल
    -0.08
    ideal
    -0.07
     bef
    -0.07
     yielding
    -0.07
     grind
    -0.07
     शिव
    -0.07
    POSITIVE LOGITS
     graag
    0.11
     مني
    0.11
     منك
    0.10
    知道
    0.09
     Mother
    0.08
     tahu
    0.08
     assistance
    0.08
     IA
    0.08
     منا
    0.08
     clarification
    0.08
    Activations Density 0.125%

    No Known Activations