© 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. 958
    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
     unh
    -0.07
    pipe
    -0.07
     неч
    -0.07
    BIG
    -0.07
    _photo
    -0.07
    Clark
    -0.07
    dur
    -0.07
    Compass
    -0.07
     לנו
    -0.07
     nam
    -0.07
    POSITIVE LOGITS
    য়ে
    0.09
    ள்வ
    0.08
     pinpoint
    0.08
     adversity
    0.07
    য়ে
    0.07
     tome
    0.07
     cons
    0.07
     प्र
    0.07
    utf
    0.07
     prank
    0.07
    Activations Density 0.000%

    No Known Activations