© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 19040
    Prev
    Next
    INDEX
    Explanations

    Code related to heaps

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ättre
    -0.10
    �제
    -0.09
    פּר
    -0.09
    -eji
    -0.09
     betere
    -0.09
    тө
    -0.09
    פּל
    -0.08
     ಮಾಡಿದ್ದಾರೆ
    -0.08
    ნახ
    -0.08
     ಹೇಳಿದರು
    -0.08
    POSITIVE LOGITS
    _mar
    0.08
    _tuple
    0.08
     الموارد
    0.08
    	from
    0.08
    	output
    0.08
     الحجم
    0.07
    _resources
    0.07
    _resource
    0.07
     мар
    0.07
    Identification
    0.07
    Activations Density 0.000%

    No Known Activations