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. 120340
    Prev
    Next
    INDEX
    Explanations

    number

    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
    خي
    -0.08
     articul
    -0.08
     articulate
    -0.07
     ನೆರ
    -0.07
     وړاندې
    -0.07
     membres
    -0.07
     reconstruct
    -0.07
    (rr
    -0.07
     members
    -0.07
    rad
    -0.07
    POSITIVE LOGITS
     evolves
    0.14
     evolve
    0.13
     Evol
    0.12
     evolucion
    0.11
     Evolution
    0.11
     evolution
    0.10
     evolução
    0.10
     Initially
    0.10
     evol
    0.10
     evolving
    0.10
    Activations Density 0.052%

    No Known Activations