Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 111459
    Prev
    Next
    INDEX
    Explanations

    w

    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
     לז
    -0.08
     propaganda
    -0.08
     CAUSED
    -0.07
     προκα
    -0.07
    صيل
    -0.07
     kole
    -0.07
    =NULL
    -0.07
    _HEIGHT
    -0.07
    、不
    -0.07
     việc
    -0.07
    POSITIVE LOGITS
     dichas
    0.08
     Avis
    0.08
     қой
    0.08
    тва
    0.08
     Marc
    0.08
    agena
    0.08
     яг
    0.08
    的时候
    0.07
     plur
    0.07
     tâ
    0.07
    Activations Density 0.001%

    No Known Activations