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. 74598
    Prev
    Next
    INDEX
    Explanations

    interest rate

    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
     난
    -0.09
     esf
    -0.09
    нод
    -0.08
     نزدیک
    -0.08
     Fiona
    -0.08
     immaculate
    -0.08
     बित
    -0.08
    ланы
    -0.07
     Sculpt
    -0.07
    -0.07
    POSITIVE LOGITS
     percentage
    0.11
    percentage
    0.11
     juros
    0.11
     weekly
    0.11
     daily
    0.10
    Percentage
    0.10
     Daily
    0.10
     száz
    0.10
     porcentaje
    0.10
    weekly
    0.10
    Activations Density 0.015%

    No Known Activations