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. 112970
    Prev
    Next
    INDEX
    Explanations

    encoding

    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
     ego
    -0.09
    驾驶
    -0.09
    ego
    -0.09
     Ego
    -0.08
    .pan
    -0.08
    crafted
    -0.08
     опыт
    -0.08
    apọ
    -0.08
     �
    -0.08
     этого
    -0.07
    POSITIVE LOGITS
     honey
    0.09
    Mismatch
    0.09
     mismatch
    0.09
    :utf
    0.08
    =UTF
    0.08
    .UTF
    0.08
    =utf
    0.08
    hnt
    0.07
     jis
    0.07
     UTF
    0.07
    Activations Density 0.002%

    No Known Activations