© 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. 111060
    Prev
    Next
    INDEX
    Explanations

    seen

    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
    prote
    -0.08
    ವೆ
    -0.08
     ಮಾತ್ರ
    -0.08
     ઉભ
    -0.08
     മാത്രം
    -0.08
     மட்டும்
    -0.08
     Destroy
    -0.08
     prote
    -0.08
    089
    -0.08
     mmoja
    -0.07
    POSITIVE LOGITS
     några
    0.09
     Bolsa
    0.09
     SR
    0.09
     bezüglich
    0.08
     SAR
    0.08
    Regarding
    0.08
    ్స
    0.08
     grü
    0.08
     necessarily
    0.08
     whereabouts
    0.08
    Activations Density 0.021%

    No Known Activations