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. 77260
    Prev
    Next
    INDEX
    Explanations

    mathematics

    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
     자리
    -0.09
     candidature
    -0.08
     Qualcomm
    -0.08
     fermentation
    -0.08
     තු
    -0.08
     ഇത്
    -0.08
     anemia
    -0.08
     poultry
    -0.08
    classpath
    -0.07
     commander
    -0.07
    POSITIVE LOGITS
     Cant
    0.12
     Lips
    0.11
     Leb
    0.11
     densely
    0.11
     infinite
    0.11
     infinitely
    0.11
     Haus
    0.10
     Dense
    0.10
     spray
    0.10
     finit
    0.10
    Activations Density 0.014%

    No Known Activations