© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 94335
    Prev
    Next
    INDEX
    Explanations

    debugging code

    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
     surveyed
    -0.09
     staples
    -0.08
     сформ
    -0.08
    бер
    -0.07
     pastoral
    -0.07
     orbital
    -0.07
    .Car
    -0.07
     Entfernung
    -0.07
    ạnh
    -0.07
     direitos
    -0.07
    POSITIVE LOGITS
    /debug
    0.15
    _debug
    0.15
     verbosity
    0.15
     debugging
    0.15
     DEBUG
    0.15
    _DEBUG
    0.14
    	debug
    0.14
    .debug
    0.14
    DEBUG
    0.14
    Debug
    0.14
    Activations Density 0.010%

    No Known Activations