© 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. 49250
    Prev
    Next
    INDEX
    Explanations

    say per

    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
     Into
    -0.09
     Might
    -0.08
    -0.08
     wona
    -0.08
     qualcosa
    -0.08
     Of
    -0.08
     abub
    -0.08
     teléfono
    -0.08
     भएको
    -0.08
     izao
    -0.08
    POSITIVE LOGITS
     પર
    0.11
     پر
    0.10
     पर
    0.10
     por
    0.10
     по
    0.10
     ανά
    0.10
     per
    0.09
     حسب
    0.09
     للت
    0.09
    /node
    0.08
    Activations Density 0.051%
    No Known Activations