© 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. 79384
    Prev
    Next
    INDEX
    Explanations

    Dragon

    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
     methods
    -0.08
    iples
    -0.07
    árias
    -0.07
     अपन
    -0.07
     Rick
    -0.07
    ări
    -0.07
     вопросам
    -0.07
    283
    -0.07
    gas
    -0.07
     Scan
    -0.07
    POSITIVE LOGITS
     эпох
    0.09
     relóg
    0.08
     Babys
    0.08
     katon
    0.08
    ftar
    0.08
    നിയ
    0.08
    Eyes
    0.08
    Civil
    0.08
    .weapon
    0.07
    Era
    0.07
    Activations Density 0.004%

    No Known Activations