© 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. 43034
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    implicitly
    -0.08
    opian
    -0.07
     thereby
    -0.07
     specializing
    -0.07
     effecten
    -0.07
    ”（
    -0.07
    ström
    -0.07
     bệnh
    -0.07
     implicitly
    -0.07
    ”，
    -0.07
    POSITIVE LOGITS
     tampoco
    0.10
     للش
    0.10
     επίσης
    0.09
     ebenfalls
    0.09
     hingegen
    0.09
     dagegen
    0.09
     نیز
    0.09
    igg
    0.08
     كذلك
    0.08
     naman
    0.08
    Activations Density 0.140%

    No Known Activations