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. 74349
    Prev
    Next
    INDEX
    Explanations

    Computers

    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
     tadi
    -0.09
    .rh
    -0.08
     Kylie
    -0.08
    alties
    -0.08
     iph
    -0.07
     Málaga
    -0.07
     yali
    -0.07
     Montpellier
    -0.07
    રની
    -0.07
     lacked
    -0.07
    POSITIVE LOGITS
     же
    0.08
    _rows
    0.08
     groundbreaking
    0.08
    ("."
    0.08
    _found
    0.07
     cornerstone
    0.07
     নিউ
    0.07
    Stroke
    0.07
     	
    0.07
     скорость
    0.07
    Activations Density 0.015%

    No Known Activations