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. 111954
    Prev
    Next
    INDEX
    Explanations

    and ,

    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
     DIE
    -0.08
     Cim
    -0.08
     Gone
    -0.08
     بهتر
    -0.07
    ான்
    -0.07
     speziellen
    -0.07
    ทาง
    -0.07
     aplikasyon
    -0.07
     Madre
    -0.07
     பயன்ப
    -0.07
    POSITIVE LOGITS
    emoc
    0.08
    .capitalize
    0.08
    aco
    0.08
     эмо
    0.08
     ambiance
    0.08
     подчерк
    0.08
     narrator
    0.08
     emphasis
    0.07
     ту
    0.07
     parlament
    0.07
    Activations Density 0.029%

    No Known Activations