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. 12737
    Prev
    Next
    INDEX
    Explanations

    command

    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
     Stamp
    -0.09
    Ring
    -0.08
     Yusuf
    -0.08
    wallet
    -0.08
    -0.08
    washed
    -0.08
    masked
    -0.07
     Flaming
    -0.07
     estup
    -0.07
    ürgen
    -0.07
    POSITIVE LOGITS
     вним
    0.09
     Aufmerksamkeit
    0.09
     внимание
    0.09
     внимания
    0.09
     attention
    0.08
     scrutiny
    0.08
     труда
    0.08
    ali
    0.08
     сила
    0.08
     минуты
    0.07
    Activations Density 0.007%

    No Known Activations