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. 43916
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     Tamil
    -0.08
    :
    -0.07
     Bengali
    -0.07
    Selectable
    -0.07
     coming
    -0.07
     Shanghai
    -0.07
     dragged
    -0.07
    园
    -0.07
     electromagnetic
    -0.07
    福建
    -0.07
    POSITIVE LOGITS
    _RATIO
    0.10
     Ratio
    0.10
    -relative
    0.10
    Ratio
    0.09
     ratios
    0.09
     Cpu
    0.09
     relativos
    0.09
     koment
    0.09
    .relative
    0.09
    _ratio
    0.09
    Activations Density 0.036%

    No Known Activations