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. 11-RESID-POST-AA
    6. 58431
    Prev
    Next
    INDEX
    Explanations

    ass

    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
     asumir
    -0.08
     Blut
    -0.08
    amiliar
    -0.07
     atraer
    -0.07
     dejar
    -0.07
     बदलाव
    -0.07
    ాలి
    -0.07
     ct
    -0.07
     estimular
    -0.07
     αφ
    -0.07
    POSITIVE LOGITS
     Ferdinand
    0.08
     rehetra
    0.08
    voj
    0.08
    ferm
    0.07
    ope
    0.07
     možno
    0.07
     Interface
    0.07
    earch
    0.07
     particulate
    0.07
    agers
    0.07
    Activations Density 2.259%

    No Known Activations