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. 49210
    Prev
    Next
    INDEX
    Explanations

    code

    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
    zitter
    -0.08
    ぱ
    -0.08
     Wright
    -0.07
     minimal
    -0.07
    ичного
    -0.07
    jö
    -0.07
     Wol
    -0.07
     Strawberry
    -0.07
     Grau
    -0.07
    skal
    -0.07
    POSITIVE LOGITS
     endemic
    0.09
     enqueue
    0.08
     lieux
    0.08
     تھیں
    0.08
     хорошие
    0.08
    >{↵↵
    0.08
     Wend
    0.07
     रहते
    0.07
    .linspace
    0.07
     pwd
    0.07
    Activations Density 0.019%

    No Known Activations