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. 65861
    Prev
    Next
    INDEX
    Explanations

    energy

    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
     có
    -0.08
    .fabric
    -0.08
    .library
    -0.08
     stitches
    -0.07
     quilt
    -0.07
     expertly
    -0.07
    按
    -0.07
     assembler
    -0.07
     library
    -0.07
    .section
    -0.07
    POSITIVE LOGITS
     conserved
    0.11
     conservation
    0.11
     conserving
    0.10
     انرژی
    0.10
     conservación
    0.10
     energies
    0.10
     الطاقة
    0.10
     energi
    0.10
     انر
    0.10
     Conservation
    0.10
    Activations Density 0.004%

    No Known Activations