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. 102564
    Prev
    Next
    INDEX
    Explanations

    code

    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
     conceive
    -0.08
    .~
    -0.08
    .
    -0.08
    ್ನ
    -0.07
    .Command
    -0.07
    ,可以
    -0.07
    angible
    -0.07
     trained
    -0.07
    'est
    -0.07
    /.
    -0.07
    POSITIVE LOGITS
     transmis
    0.09
     gbigbe
    0.09
     vigilancia
    0.09
     吉
    0.09
     puck
    0.08
     初始化
    0.08
     aluminio
    0.08
     eps
    0.08
    ंखला
    0.08
     kaže
    0.08
    Activations Density 0.030%

    No Known Activations