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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 111615
    Prev
    Next
    INDEX
    Explanations

    Signature

    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
    িখ
    -0.09
    情
    -0.09
    тор
    -0.08
     neg
    -0.08
     timestep
    -0.08
    负
    -0.07
    有哪些
    -0.07
    促进
    -0.07
    .concat
    -0.07
    过程中
    -0.07
    POSITIVE LOGITS
     Acrobat
    0.09
    professional
    0.09
     profesional
    0.08
     украш
    0.08
    Professional
    0.08
    앤
    0.08
     حرفه
    0.08
     airy
    0.08
     إلكتر
    0.08
     scall
    0.08
    Activations Density 0.002%

    No Known Activations