© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 94455
    Prev
    Next
    INDEX
    Explanations

    paying off debt

    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
    лайда
    -0.09
    	click
    -0.08
     statistical
    -0.08
     Statistical
    -0.08
     темат
    -0.08
     Pereira
    -0.08
     заход
    -0.08
     encontros
    -0.08
    ehr
    -0.07
     вина
    -0.07
    POSITIVE LOGITS
     debts
    0.17
     debt
    0.17
    债
    0.15
    Debt
    0.14
     repayment
    0.13
     Debt
    0.13
     deuda
    0.13
     dívida
    0.12
     задолж
    0.11
     taxes
    0.11
    Activations Density 0.016%

    No Known Activations