© 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. 29499
    Prev
    Next
    INDEX
    Explanations

    andas

    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
     politici
    -0.08
    hnt
    -0.08
     documented
    -0.08
     accessed
    -0.08
     hack
    -0.08
    hada
    -0.08
     haze
    -0.07
     temor
    -0.07
     hue
    -0.07
     задум
    -0.07
    POSITIVE LOGITS
     encyclopedia
    0.08
     Doppel
    0.08
    どう
    0.08
    .converter
    0.07
     inhab
    0.07
    .region
    0.07
    repository
    0.07
     inhabit
    0.07
    .uf
    0.07
    repos
    0.07
    Activations Density 0.006%

    No Known Activations