© 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 EvalsExportsinterp-engineNEWAPI 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. 71142
    Prev
    Next
    INDEX
    Explanations

    sponsored

    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
    contain
    -0.08
     exemplar
    -0.07
     здан
    -0.07
     Raiders
    -0.07
     whare
    -0.07
    checking
    -0.07
     klar
    -0.07
    aranja
    -0.07
     Waters
    -0.07
     wux
    -0.07
    POSITIVE LOGITS
    Oops
    0.09
    _literals
    0.08
    익
    0.08
    “Oh
    0.08
    GHz
    0.08
     Securities
    0.07
     GHz
    0.07
    Selective
    0.07
     quasi
    0.07
    -inline
    0.07
    Activations Density 0.001%

    No Known Activations