© 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. 108222
    Prev
    Next
    INDEX
    Explanations

    Bosphorus strait

    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
     barr
    -0.08
    Stan
    -0.08
     absentee
    -0.08
    George
    -0.08
     hon
    -0.08
    비
    -0.07
     honing
    -0.07
     срока
    -0.07
     ballot
    -0.07
    @Spring
    -0.07
    POSITIVE LOGITS
     Compart
    0.08
     ভাগ
    0.08
     divides
    0.07
     impart
    0.07
    reiche
    0.07
     sise
    0.07
     Algo
    0.07
     imperative
    0.07
     adulto
    0.07
     partition
    0.07
    Activations Density 0.001%

    No Known Activations