© 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. 5715
    Prev
    Next
    INDEX
    Explanations

    points

    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
     coś
    -0.09
     específico
    -0.08
     используется
    -0.08
     был
    -0.08
     влияет
    -0.08
     понадобится
    -0.08
     משתמש
    -0.08
     něco
    -0.08
     неш
    -0.08
     eentje
    -0.08
    POSITIVE LOGITS
     points
    0.14
     {(
    0.14
     satisfying
    0.13
    .points
    0.13
    (points
    0.13
    Points
    0.12
     الذين
    0.12
    points
    0.12
     Punkte
    0.12
     puntos
    0.12
    Activations Density 0.062%

    No Known Activations