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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-RESID-POST-AA
    6. 19324
    Prev
    Next
    INDEX
    Explanations

    Numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ilum
    -0.09
    hlung
    -0.09
    ઃ
    -0.08
     النار
    -0.08
     مند
    -0.08
     үнд
    -0.08
     ponta
    -0.08
    _BGR
    -0.08
     recital
    -0.08
     tú
    -0.08
    POSITIVE LOGITS
     particular
    0.08
     VERSION
    0.08
     chosen
    0.08
     specifieke
    0.08
     SPEC
    0.08
    stack
    0.07
     specifiek
    0.07
    bin
    0.07
    version
    0.07
    positive
    0.07
    Activations Density 0.086%

    No Known Activations