© 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. 3-RESID-POST-AA
    6. 1413
    Prev
    Next
    INDEX
    Explanations

    ответ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consequences
    -0.07
     prescribing
    -0.07
     informatique
    -0.07
     inspir
    -0.07
     inert
    -0.07
     கண
    -0.07
     acuerdo
    -0.07
    Minister
    -0.07
     अनुसार
    -0.07
     pres
    -0.07
    POSITIVE LOGITS
     Regent
    0.08
     zuhause
    0.08
     selain
    0.08
     malt
    0.08
    除了
    0.08
    吾
    0.08
    polygon
    0.08
    (poly
    0.08
     joku
    0.08
     તો
    0.07
    Activations Density 0.002%

    No Known Activations