© 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. 23-RESID-POST-AA
    11. 47659
    Prev
    Next
    INDEX
    Explanations

    say "на"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    રાજ
    -0.08
    egiatan
    -0.08
    ANDA
    -0.08
    &auml
    -0.08
    akay
    -0.07
     Mixer
    -0.07
    hete
    -0.07
    ้น
    -0.07
    andag
    -0.07
    (styles
    -0.07
    POSITIVE LOGITS
     um
    0.19
     o
    0.16
     на
    0.15
     sebesar
    0.14
     بنسبة
    0.14
     κατά
    0.14
    Um
    0.14
     Um
    0.12
    	o
    0.11
     ëm
    0.11
    Activations Density 0.011%

    No Known Activations