© 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. 47915
    Prev
    Next
    INDEX
    Explanations

    code documentation examples

    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
     subjet
    -0.09
     radians
    -0.08
     casque
    -0.08
     whisk
    -0.08
     competencias
    -0.08
     Facial
    -0.08
     aa
    -0.08
     isot
    -0.08
     facial
    -0.08
     recombinant
    -0.08
    POSITIVE LOGITS
    数据库
    0.20
     database
    0.17
    (database
    0.17
    .database
    0.17
     databases
    0.17
    SQLite
    0.17
    Database
    0.16
    database
    0.16
    .sqlite
    0.15
    _DATABASE
    0.15
    Activations Density 0.053%

    No Known Activations