© 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. 70442
    Prev
    Next
    INDEX
    Explanations

    armor

    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
    _LONG
    -0.09
    美
    -0.08
    තු
    -0.08
    ఖ
    -0.08
    -long
    -0.08
    क्क
    -0.08
    rịta
    -0.08
    gru
    -0.07
    anos
    -0.07
    เกอร์
    -0.07
    POSITIVE LOGITS
     rekla
    0.08
     maksimal
    0.07
     dispone
    0.07
     Stel
    0.07
     dada
    0.07
     dispositions
    0.07
     megfe
    0.07
     dispos
    0.07
     dissip
    0.07
     classement
    0.07
    Activations Density 0.001%

    No Known Activations