© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30064
    Prev
    Next
    INDEX
    Explanations

    Finding family

    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
     stap
    -0.09
     použív
    -0.08
    (icon
    -0.08
     raster
    -0.08
     sharpening
    -0.08
     počas
    -0.08
    (Animation
    -0.08
    ixi
    -0.08
     vitória
    -0.08
     vooruit
    -0.08
    POSITIVE LOGITS
     genealog
    0.12
     ancestry
    0.12
     ancestral
    0.11
     siblings
    0.11
     inherited
    0.11
    父
    0.11
     पिता
    0.11
     reunion
    0.10
     genealogy
    0.10
     ancestors
    0.10
    Activations Density 0.078%

    No Known Activations