© 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. 114114
    Prev
    Next
    INDEX
    Explanations

    set

    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
    Ан
    -0.08
    sap
    -0.08
    HV
    -0.08
     eighteen
    -0.08
    Sb
    -0.08
    kaart
    -0.08
     HV
    -0.07
    oloh
    -0.07
    stav
    -0.07
     HOM
    -0.07
    POSITIVE LOGITS
     kết
    0.09
    #elif
    0.08
     ndim
    0.08
    	buff
    0.08
    édia
    0.08
    ibl
    0.08
     cudd
    0.08
     וגם
    0.07
    	uint
    0.07
     ٿي
    0.07
    Activations Density 0.000%

    No Known Activations