© 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. 63780
    Prev
    Next
    INDEX
    Explanations

    Period

    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
    슬
    -0.08
    wl
    -0.08
     Traverse
    -0.08
     만큼
    -0.08
    RH
    -0.08
     traj
    -0.08
    ██
    -0.08
    wn
    -0.08
    wc
    -0.07
     neuer
    -0.07
    POSITIVE LOGITS
    emenangan
    0.08
    .finish
    0.07
     assuming
    0.07
    eree
    0.07
     finished
    0.07
    romy
    0.07
     sends
    0.07
    ებიან
    0.07
    ả
    0.07
    oroč
    0.07
    Activations Density 0.155%

    No Known Activations