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. 109824
    Prev
    Next
    INDEX
    Explanations

    处理

    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
     chemically
    -0.08
     extremo
    -0.08
     Roch
    -0.07
    lection
    -0.07
     Bt
    -0.07
    เห
    -0.07
     Toe
    -0.07
    poster
    -0.07
    ount
    -0.07
    -producing
    -0.07
    POSITIVE LOGITS
    denk
    0.08
     mõ
    0.08
     プ
    0.08
     инструкция
    0.08
     Architect
    0.07
    ügel
    0.07
    ಅ
    0.07
     предназнач
    0.07
     Instruction
    0.07
     Playground
    0.07
    Activations Density 0.004%

    No Known Activations