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. 43460
    Prev
    Next
    INDEX
    Explanations

    multiple choice answers

    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
     cognition
    -0.09
     studs
    -0.08
    hape
    -0.08
    Attribute
    -0.07
     cura
    -0.07
    Detection
    -0.07
    .mod
    -0.07
    lyn
    -0.07
    Shape
    -0.07
    Deployment
    -0.07
    POSITIVE LOGITS
     fechamento
    0.09
     діяль
    0.08
     direito
    0.08
     ẹ
    0.08
     कि
    0.08
     ì
    0.08
     ECG
    0.08
     грам
    0.08
     вип
    0.08
     í
    0.08
    Activations Density 0.050%

    No Known Activations