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. 90103
    Prev
    Next
    INDEX
    Explanations

    Exponentiation and logarithms

    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
     expense
    -0.07
    फल
    -0.07
     Maestro
    -0.07
    Diag
    -0.07
     диаг
    -0.07
     svårt
    -0.07
    大发
    -0.07
     kateg
    -0.07
     σχ
    -0.07
     scholarships
    -0.07
    POSITIVE LOGITS
     Slowly
    0.08
     eyebrow
    0.08
    .Small
    0.08
    -profile
    0.08
     complac
    0.08
    ją
    0.08
     iji
    0.07
     yüzde
    0.07
     inflação
    0.07
    .DO
    0.07
    Activations Density 0.024%

    No Known Activations