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. 44008
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
    �
    -0.08
    িমান
    -0.08
     widen
    -0.07
    -wide
    -0.07
    這
    -0.07
    	var
    -0.07
     qeyd
    -0.07
    wide
    -0.07
     Veh
    -0.07
     Worship
    -0.07
    POSITIVE LOGITS
     Medieval
    0.08
    alach
    0.08
     bof
    0.08
     Escolar
    0.08
     quân
    0.08
     Möglich
    0.07
    ทัน
    0.07
    oso
    0.07
     orchard
    0.07
     Hoffman
    0.07
    Activations Density 0.047%

    No Known Activations