© 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. 30230
    Prev
    Next
    INDEX
    Explanations

    rest

    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
     victory
    -0.08
     battle
    -0.07
    Plac
    -0.07
     indiqu
    -0.07
    垃圾
    -0.07
     importer
    -0.07
    .Dat
    -0.07
     Mermaid
    -0.07
    ка
    -0.07
    ækker
    -0.07
    POSITIVE LOGITS
     torque
    0.09
     voorzichtig
    0.08
     appreci
    0.08
     progressively
    0.08
     creciente
    0.08
     ratt
    0.08
    oment
    0.08
    vény
    0.08
    Torque
    0.08
     Ross
    0.08
    Activations Density 0.002%

    No Known Activations