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

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 19255
    Prev
    Next
    INDEX
    Explanations

    math equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )
    -0.08
     I'd
    -0.08
     differently
    -0.08
    ),
    -0.07
    ="
    -0.07
     let's
    -0.07
     possibly
    -0.07
     ensure
    -0.07
    ):
    -0.07
     in
    -0.07
    POSITIVE LOGITS
     inderdaad
    0.11
    ская
    0.09
    ાયું
    0.09
     પડે
    0.08
    вад
    0.08
    ‍ക്കും
    0.08
     genauso
    0.08
     explicado
    0.08
     daí
    0.08
     Singer
    0.08
    Activations Density 0.085%

    No Known Activations