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. 65178
    Prev
    Next
    INDEX
    Explanations

    prisons and concentration camps

    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
     ज्य
    -0.07
    Mg
    -0.07
     charge
    -0.07
    Dims
    -0.07
     Må
    -0.07
     개
    -0.07
     charges
    -0.07
     Charges
    -0.07
     deliberately
    -0.07
     contenant
    -0.07
    POSITIVE LOGITS
     დან
    0.08
     тас
    0.08
    ,人
    0.08
    archar
    0.08
     rope
    0.08
    (chr
    0.08
    -gray
    0.08
     до
    0.08
     Bruss
    0.08
    APL
    0.08
    Activations Density 0.006%

    No Known Activations