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

    Neuronpedia

    APICircuit 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. 106289
    Prev
    Next
    INDEX
    Explanations

    false

    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
     suffers
    -0.07
    巡
    -0.07
     outlet
    -0.07
     MET
    -0.07
     assigns
    -0.07
     interpol
    -0.07
    分
    -0.07
     timestep
    -0.07
    termin
    -0.07
     interpolation
    -0.06
    POSITIVE LOGITS
     empfohlen
    0.09
     þe
    0.08
     práct
    0.08
     minced
    0.08
     recomienda
    0.08
    -Germain
    0.08
    icios
    0.08
    <Scalars
    0.08
     Germ
    0.08
    	Toast
    0.08
    Activations Density 0.013%

    No Known Activations