© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 65376
    Prev
    Next
    INDEX
    Explanations

    concrete

    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
    -0.08
     ते
    -0.08
     वे
    -0.08
     नै
    -0.07
     pra
    -0.07
    beh
    -0.07
    owing
    -0.07
     kamb
    -0.07
     बाव
    -0.07
     Marino
    -0.07
    POSITIVE LOGITS
     tangible
    0.09
     eg
    0.09
     concr
    0.08
     concrete
    0.08
     Eg
    0.08
    uset
    0.08
     concreta
    0.08
    ніше
    0.08
     sober
    0.08
    iou
    0.08
    Activations Density 0.008%
    No Known Activations