© 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. 79449
    Prev
    Next
    INDEX
    Explanations

    Iberian Peninsula

    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
    .ful
    -0.07
    ående
    -0.07
    keep
    -0.07
     PURE
    -0.07
    worthiness
    -0.07
    keepers
    -0.07
     keep
    -0.07
    (reset
    -0.07
    iyas
    -0.07
    যোগ্য
    -0.07
    POSITIVE LOGITS
     peninsula
    0.13
     Peninsula
    0.11
    -shaped
    0.08
     desempen
    0.08
     પરથી
    0.08
     encant
    0.08
     Schleswig
    0.08
     stran
    0.08
     phosphorus
    0.08
     Cl
    0.08
    Activations Density 0.007%

    No Known Activations