Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 45078
    Prev
    Next
    INDEX
    Explanations

    offset

    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
     поб
    -0.08
    แก
    -0.08
    -0.08
     גוף
    -0.08
    ůj
    -0.08
     Accelerator
    -0.07
     이야
    -0.07
     nonstop
    -0.07
    orgetown
    -0.07
    件
    -0.07
    POSITIVE LOGITS
     shortcomings
    0.08
     parcial
    0.08
     parcialmente
    0.08
     loneliness
    0.08
    balance
    0.07
    一下
    0.07
     offset
    0.07
    Cancelled
    0.07
     añad
    0.07
     необходимости
    0.07
    Activations Density 0.023%

    No Known Activations