Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12789
    Prev
    Next
    INDEX
    Explanations

    Heat

    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
     Noah
    -0.07
     Bab
    -0.07
     finger
    -0.07
     Pamela
    -0.07
     нач
    -0.07
    df
    -0.07
    skb
    -0.07
    ฯ
    -0.07
     Coch
    -0.07
    Bab
    -0.07
    POSITIVE LOGITS
    帯
    0.09
    �
    0.08
    棒
    0.08
    Stamp
    0.08
    waves
    0.07
     выполнения
    0.07
    ache
    0.07
    ালে
    0.07
    resas
    0.07
    突
    0.07
    Activations Density 0.017%

    No Known Activations