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. 44032
    Prev
    Next
    INDEX
    Explanations

    ears

    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
     UT
    -0.08
    wania
    -0.08
    ுடன்
    -0.08
     herein
    -0.08
     eigener
    -0.07
     citoy
    -0.07
     receptors
    -0.07
     theo
    -0.07
    ersen
    -0.07
     жить
    -0.07
    POSITIVE LOGITS
    ETS
    0.08
     నమ
    0.08
    _TAC
    0.07
    pok
    0.07
     ఉన్నాయి
    0.07
     insulation
    0.07
    /out
    0.07
    ece
    0.07
     ڊ
    0.07
    ifes
    0.07
    Activations Density 0.001%

    No Known Activations