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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 106304
    Prev
    Next
    INDEX
    Explanations

    scene

    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
     нит
    -0.09
     муч
    -0.09
    ünft
    -0.08
    Mutable
    -0.08
     нем
    -0.08
     акт
    -0.08
    NA
    -0.08
     Underground
    -0.08
     платить
    -0.08
    .Mutable
    -0.08
    POSITIVE LOGITS
     modes
    0.13
     Modes
    0.13
     Mode
    0.13
     режима
    0.12
    mode
    0.12
     режим
    0.12
    	mode
    0.12
     mode
    0.11
     режиме
    0.11
     modalità
    0.11
    Activations Density 0.049%

    No Known Activations