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. 188
    Prev
    Next
    INDEX
    Explanations

    walking speed

    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
    upplier
    -0.07
    )-(
    -0.07
     Mother
    -0.07
     Valve
    -0.07
     %[
    -0.07
    -metal
    -0.07
     spezif
    -0.07
    र्ख
    -0.07
     PCB
    -0.07
    Mother
    -0.07
    POSITIVE LOGITS
     pace
    0.13
     brisk
    0.12
     stroll
    0.11
     gait
    0.11
     strolling
    0.11
     jogging
    0.10
     cadence
    0.10
     leisurely
    0.10
     pacing
    0.10
     ritmo
    0.10
    Activations Density 0.011%

    No Known Activations