© 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 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. 50178
    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     but
    -0.09
     কিন্তু
    -0.09
     pero
    -0.08
     но
    -0.08
    /%
    -0.08
     కానీ
    -0.08
     ولكن
    -0.08
     ×
    -0.08
     или
    -0.08
     पण
    -0.08
    POSITIVE LOGITS
    Evaluate
    0.09
    Initialization
    0.09
     Evaluate
    0.09
     Initialize
    0.09
    Initialize
    0.09
    Inicio
    0.09
    Considering
    0.08
    خاذ
    0.08
    Current
    0.08
    Overall
    0.08
    Activations Density 0.004%

    No Known Activations