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. 45077
    Prev
    Next
    INDEX
    Explanations

    shapes

    np_max-act · gemini-2.0-flash

    attends from the penultimate token in a sequence to a token with similar semantic meaning earlier in the sequence.

    oai_attention-head · gpt-4oTriggered by @mlfinancebook
    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
     CPT
    -0.09
     இதில்
    -0.08
     производится
    -0.08
     fremst
    -0.08
     இடம்பெ
    -0.08
     பட
    -0.08
     Manor
    -0.08
     manor
    -0.08
     ذلك
    -0.08
     இன்று
    -0.08
    POSITIVE LOGITS
     limiting
    0.09
     cavities
    0.07
    Available
    0.07
     corredores
    0.07
     maxima
    0.07
    पास
    0.07
     confinement
    0.07
     carving
    0.07
     centra
    0.07
     curvature
    0.07
    Activations Density 0.055%

    No Known Activations