© 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. 114145
    Prev
    Next
    INDEX
    Explanations

    fulness

    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
    раг
    -0.09
     crafted
    -0.08
     republican
    -0.08
     ಕಾರ್ಯಕ್ರಮ
    -0.08
    хо
    -0.08
    न्होंने
    -0.08
     abb
    -0.08
     entretien
    -0.07
    နိုင်
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    vine
    0.08
    brit
    0.08
    Pen
    0.07
     الفي
    0.07
     existential
    0.07
    β
    0.07
     net
    0.07
     germ
    0.07
    SUR
    0.07
     brainstorm
    0.07
    Activations Density 0.000%

    No Known Activations