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. 111910
    Prev
    Next
    INDEX
    Explanations

    coding principles

    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
     लै
    -0.08
     Workplace
    -0.07
    trial
    -0.07
    、日本
    -0.07
     Bharat
    -0.07
    sphere
    -0.07
    cw
    -0.07
    homes
    -0.07
     workplace
    -0.07
     labs
    -0.07
    POSITIVE LOGITS
     চান
    0.12
    用途
    0.09
     хотите
    0.09
     Zweck
    0.09
     want
    0.09
     reuse
    0.08
     semantics
    0.08
     операция
    0.08
     wanting
    0.08
     besoins
    0.08
    Activations Density 0.046%

    No Known Activations