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. 59466
    Prev
    Next
    INDEX
    Explanations

    remainder is zero

    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
    。↵↵
    -0.08
    020
    -0.07
    }$
    -0.07
     errands
    -0.07
    osure
    -0.07
     Pegasus
    -0.07
    484
    -0.07
     décid
    -0.07
    飞机
    -0.07
    Anchor
    -0.07
    POSITIVE LOGITS
     courteous
    0.08
     obtenido
    0.08
    roff
    0.08
    ρια
    0.07
     ho
    0.07
    คือ
    0.07
     лиц
    0.07
     Lawson
    0.07
     quién
    0.07
    ENGE
    0.07
    Activations Density 0.003%

    No Known Activations