© 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. 1020
    Prev
    Next
    INDEX
    Explanations

    frequency

    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
     aportar
    -0.08
     Included
    -0.08
     vers
    -0.07
    bureau
    -0.07
     Mirror
    -0.07
     Cot
    -0.07
     Murder
    -0.07
     columnist
    -0.07
     Est
    -0.07
     Parsed
    -0.07
    POSITIVE LOGITS
     పల
    0.08
     తెలుగు
    0.08
     decentralized
    0.08
     waveform
    0.08
     deviations
    0.08
     нест
    0.08
     ওঠ
    0.08
    Deviation
    0.08
     தமிழ்
    0.08
    _IDLE
    0.08
    Activations Density 0.001%

    No Known Activations