© 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. 70163
    Prev
    Next
    INDEX
    Explanations

    standing

    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
    τυ
    -0.08
    ં
    -0.08
     использованием
    -0.07
    veld
    -0.07
     Muito
    -0.07
    /the
    -0.07
    經
    -0.07
    _percent
    -0.07
     esteve
    -0.07
    ابر
    -0.07
    POSITIVE LOGITS
    endif
    0.08
     congressional
    0.08
     sht
    0.07
     pojed
    0.07
     issue
    0.07
     cm
    0.07
     politischen
    0.07
     politik
    0.07
    ypass
    0.07
     individ
    0.07
    Activations Density 0.003%

    No Known Activations