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. 111739
    Prev
    Next
    INDEX
    Explanations

    Chinese and technical writing

    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
     mortgages
    -0.09
     tratamentos
    -0.09
     spruce
    -0.09
     pudd
    -0.09
     traitements
    -0.08
     Savannah
    -0.08
    יחות
    -0.08
     textos
    -0.08
     alley
    -0.08
    mig
    -0.08
    POSITIVE LOGITS
     iterative
    0.10
     प्रार
    0.09
    Helpers
    0.08
     decisions
    0.08
     iter
    0.08
     generating
    0.08
    _GENER
    0.08
     decision
    0.07
     शुरू
    0.07
     ಆರಂಭ
    0.07
    Activations Density 0.003%

    No Known Activations