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. 75316
    Prev
    Next
    INDEX
    Explanations

    Explosions and flammable materials

    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
    President
    -0.09
     president
    -0.08
     राजा
    -0.07
     President
    -0.07
     regal
    -0.07
     invierno
    -0.07
     grooming
    -0.07
     otoño
    -0.07
     verano
    -0.07
     King
    -0.07
    POSITIVE LOGITS
     বিপ
    0.09
     poderia
    0.09
     concentração
    0.09
     mixtures
    0.09
     смеси
    0.08
     концентра
    0.08
     раств
    0.08
     mixture
    0.08
     explos
    0.08
     হিস
    0.08
    Activations Density 0.005%

    No Known Activations