© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23-RESID-POST-AA
    11. 6447
    Prev
    Next
    INDEX
    Explanations

    打

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    บริ
    -0.08
    τουργ
    -0.08
     clicar
    -0.08
     okviru
    -0.08
    ъв
    -0.07
     nngwe
    -0.07
     соответств
    -0.07
     financiamento
    -0.07
     dowl
    -0.07
     შეხვედ
    -0.07
    POSITIVE LOGITS
    算
    0.09
     Quant
    0.08
    Bi
    0.07
    giv
    0.07
    Quant
    0.07
    isti
    0.07
     pointless
    0.07
    ust
    0.07
     quantified
    0.07
    quant
    0.07
    Activations Density 0.001%

    No Known Activations