© 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. 47706
    Prev
    Next
    INDEX
    Explanations

    Nuclear and atomic physics

    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
    реш
    -0.08
     решений
    -0.08
     Wach
    -0.08
     boating
    -0.08
    ಂಬ
    -0.07
     offic
    -0.07
    ಿರುವ
    -0.07
     topar
    -0.07
    לו
    -0.07
     duty
    -0.07
    POSITIVE LOGITS
     nuclé
    0.12
    _particles
    0.11
     nucléaire
    0.11
     nucle
    0.11
     Nuclear
    0.11
     nuclei
    0.11
     nuclear
    0.11
     particles
    0.10
     nucleus
    0.10
     partículas
    0.10
    Activations Density 0.008%

    No Known Activations