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. 111850
    Prev
    Next
    INDEX
    Explanations

    scientific notation and symbols

    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
     endorse
    -0.07
    огод
    -0.07
    ks
    -0.06
    structor
    -0.06
     goog
    -0.06
    forma
    -0.06
    12
    -0.06
     geometry
    -0.06
     @
    -0.06
     suppose
    -0.06
    POSITIVE LOGITS
     наоборот
    0.10
     extremes
    0.10
    ammu
    0.10
     ironically
    0.10
     բայց
    0.09
    лишком
    0.09
     Conversely
    0.09
     juist
    0.09
     baý
    0.09
    лайды
    0.09
    Activations Density 0.072%

    No Known Activations