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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 75345
    Prev
    Next
    INDEX
    Explanations

    lymphedema

    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
    <footer
    -0.09
     Looking
    -0.09
     klientów
    -0.08
     abay
    -0.08
    _go
    -0.08
     marriages
    -0.08
     -.
    -0.08
    _footer
    -0.08
     olhando
    -0.08
    /Footer
    -0.07
    POSITIVE LOGITS
    .initial
    0.10
    initial
    0.09
    ρά
    0.09
    (initial
    0.08
     initial
    0.08
    	initial
    0.08
     swelling
    0.08
     حجم
    0.08
    初
    0.08
    INITIAL
    0.08
    Activations Density 0.005%

    No Known Activations