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. 49165
    Prev
    Next
    INDEX
    Explanations

    sorry

    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
     Lights
    -0.08
    _et
    -0.08
    tz
    -0.08
    pri
    -0.08
    ctie
    -0.07
     prevents
    -0.07
    azines
    -0.07
    -axis
    -0.07
    :disable
    -0.07
     tz
    -0.07
    POSITIVE LOGITS
     दु�
    0.12
     दुख
    0.10
     heartbreak
    0.10
     stirred
    0.09
     turmoil
    0.09
     unfortunate
    0.09
     heartbreaking
    0.09
     hardship
    0.08
     luk
    0.08
     hardships
    0.08
    Activations Density 0.009%

    No Known Activations