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. 23-RESID-POST-AA
    6. 130820
    Prev
    Next
    INDEX
    Explanations

    spinal injuries

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     espalda
    -0.10
     posture
    -0.10
     joints
    -0.09
     FLOOR
    -0.09
     directional
    -0.09
     back
    -0.09
     vloer
    -0.08
     backlinks
    -0.08
    culoskeletal
    -0.08
    кими
    -0.08
    POSITIVE LOGITS
     Th
    0.10
    -Th
    0.09
     bursting
    0.09
    -th
    0.09
     thor
    0.09
     burst
    0.09
     thaw
    0.08
     lesion
    0.08
    _th
    0.08
    Th
    0.08
    Activations Density 0.004%

    No Known Activations