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. 48987
    Prev
    Next
    INDEX
    Explanations

    least

    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
    чес
    -0.08
    至
    -0.07
     Маг
    -0.07
    irmek
    -0.07
    keun
    -0.07
     분위
    -0.07
     people's
    -0.07
     சாத
    -0.07
     үст
    -0.07
     .....
    -0.07
    POSITIVE LOGITS
     minuut
    0.08
     dozen
    0.08
     NAV
    0.08
    /poly
    0.08
     blk
    0.08
     पोल
    0.08
     nove
    0.08
    /ml
    0.08
    η
    0.08
     hita
    0.08
    Activations Density 0.011%

    No Known Activations