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. 56014
    Prev
    Next
    INDEX
    Explanations

    with

    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
     venc
    -0.08
     STI
    -0.08
    vection
    -0.08
    বিদ
    -0.08
     ps
    -0.07
    icked
    -0.07
    odian
    -0.07
     BJ
    -0.07
    ps
    -0.07
     Quit
    -0.07
    POSITIVE LOGITS
     Praise
    0.08
    Items
    0.08
    138
    0.08
     Icons
    0.07
     supplémentaire
    0.07
    ər
    0.07
     прап
    0.07
     substantive
    0.07
     ï
    0.07
     Items
    0.07
    Activations Density 0.004%

    No Known Activations