© 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. 69898
    Prev
    Next
    INDEX
    Explanations

    round

    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
    .dec
    -0.08
    Strip
    -0.08
    钟
    -0.08
     versatile
    -0.08
    dec
    -0.08
    Minute
    -0.08
    Cock
    -0.08
    Minutes
    -0.08
    分钟
    -0.08
    Ngày
    -0.07
    POSITIVE LOGITS
     the
    0.08
     SPR
    0.08
    ाकार
    0.08
     mp
    0.08
     desire
    0.08
     निर्देशन
    0.08
     MPC
    0.08
    _OT
    0.07
     simultaneous
    0.07
     sparse
    0.07
    Activations Density 0.001%

    No Known Activations