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. 60965
    Prev
    Next
    INDEX
    Explanations

    religious texts

    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
     u
    -0.08
    u
    -0.08
    semin
    -0.07
     Spread
    -0.07
    484
    -0.07
    487
    -0.07
     Save
    -0.06
    seit
    -0.06
     eu
    -0.06
     Joint
    -0.06
    POSITIVE LOGITS
     rightful
    0.13
     deserved
    0.10
     warranted
    0.09
    ραί
    0.09
     apabila
    0.09
     mérite
    0.09
     પડે
    0.09
     gouver
    0.08
     delir
    0.08
     deserving
    0.08
    Activations Density 0.007%

    No Known Activations