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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48487
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دڙ
    -0.11
    n't
    -0.10
    ful
    -0.09
    iagn
    -0.09
    fulness
    -0.09
    setzung
    -0.09
    പ്പെട്ട
    -0.09
    പ്പെടുത്തിയ
    -0.09
    മയം
    -0.08
    داشت
    -0.08
    POSITIVE LOGITS
     प्रक्र
    0.08
    平方
    0.08
    ˆ
    0.08
     cómo
    0.08
     strength
    0.07
    _strength
    0.07
     необходимых
    0.07
     þessu
    0.07
     süreç
    0.07
     що
    0.07
    Activations Density 0.091%

    No Known Activations