© 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. 3-RESID-POST-AA
    11. 1153
    Prev
    Next
    INDEX
    Explanations

    ({

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     favors
    -0.08
    Vp
    -0.08
     vision
    -0.07
     spe
    -0.07
    Coeff
    -0.07
    _exist
    -0.07
     execute
    -0.07
    管
    -0.07
     होंगे
    -0.07
     Vision
    -0.07
    POSITIVE LOGITS
     pedra
    0.08
     motherhood
    0.08
     Abraham
    0.08
     Yeh
    0.08
     Kyr
    0.07
     Toute
    0.07
     architecture
    0.07
    mei
    0.07
     architects
    0.07
     Amir
    0.07
    Activations Density 0.000%

    No Known Activations