© 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. 11-RESID-POST-AA
    11. 63844
    Prev
    Next
    INDEX
    Explanations

    factor pairs

    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
    _supported
    -0.09
     Responsibilities
    -0.08
     Birch
    -0.08
     də
    -0.08
     ginagamit
    -0.08
     hipot
    -0.08
     cutters
    -0.08
    istern
    -0.08
     Connecting
    -0.08
    əni
    -0.08
    POSITIVE LOGITS
    Qo
    0.08
     obvious
    0.07
     net
    0.07
    Qtd
    0.07
     engine
    0.07
     mirrored
    0.07
    engine
    0.07
     feedback
    0.07
    Q
    0.07
    Net
    0.07
    Activations Density 0.024%

    No Known Activations