© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 64538
    Prev
    Next
    INDEX
    Explanations

    wild animals

    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
     viral
    -0.08
     misleading
    -0.07
     अनुम
    -0.07
    Boolean
    -0.07
    -0.07
     trunc
    -0.07
     Masc
    -0.07
    ಿಡ
    -0.07
     contém
    -0.07
    盒
    -0.07
    POSITIVE LOGITS
     occasional
    0.09
     endangered
    0.09
     scarcity
    0.08
     predomin
    0.08
     сорта
    0.08
    rare
    0.08
     abundance
    0.08
     outdoor
    0.08
     prevalence
    0.08
    Outdoor
    0.08
    Activations Density 0.041%
    No Known Activations