© 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. 113368
    Prev
    Next
    INDEX
    Explanations

    Numbers 11-19

    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
    רת
    -0.09
    Vegas
    -0.09
    ונה
    -0.09
    τικής
    -0.08
    יטת
    -0.08
    vart
    -0.08
    azo
    -0.08
    ideo
    -0.08
    _VM
    -0.08
    uzet
    -0.08
    POSITIVE LOGITS
     constant
    0.09
     эпох
    0.08
     uses
    0.08
     konst
    0.08
     Constant
    0.08
     builds
    0.07
     уменьш
    0.07
     насы
    0.07
     преобраз
    0.07
     invokes
    0.07
    Activations Density 0.005%

    No Known Activations