© 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. 15-RESID-POST-AA
    11. 16664
    Prev
    Next
    INDEX
    Explanations

    \

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     प्रकाश
    -0.08
     preferably
    -0.08
     قيام
    -0.08
    .latitude
    -0.08
     ýü
    -0.08
    @Suppress
    -0.08
     നേട
    -0.07
     Aufnahme
    -0.07
    κυ
    -0.07
    иций
    -0.07
    POSITIVE LOGITS
    部分
    0.09
     tails
    0.09
     кус
    0.09
     morceaux
    0.09
     spline
    0.08
     části
    0.08
    Compiled
    0.08
     부분
    0.08
     supposed
    0.08
     parab
    0.08
    Activations Density 0.020%

    No Known Activations