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. 109176
    Prev
    Next
    INDEX
    Explanations

    ou

    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
    ১০
    -0.07
     பாட
    -0.07
    ofen
    -0.07
    eu
    -0.07
    ‫
    -0.07
    aes
    -0.07
    icts
    -0.07
     Amanda
    -0.07
    Œ
    -0.07
    æ
    -0.07
    POSITIVE LOGITS
     miesto
    0.09
     stuff
    0.08
     cond
    0.08
    哈哈
    0.07
     компонент
    0.07
    iennes
    0.07
    _TC
    0.07
     Autos
    0.07
     hehe
    0.07
     прид
    0.07
    Activations Density 0.690%

    No Known Activations