© 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. 19-RESID-POST-AA
    11. 22654
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ിയും
    -0.10
    ியும்
    -0.09
     בדיוק
    -0.09
    ીએ
    -0.08
     precisão
    -0.08
    യും
    -0.08
    ികളും
    -0.08
    除
    -0.08
     emprego
    -0.08
    }=
    -0.07
    POSITIVE LOGITS
     বেশি
    0.21
     preferential
    0.21
     rohkem
    0.19
     enemmän
    0.19
    favor
    0.19
     favors
    0.19
     favor
    0.19
     больше
    0.19
     predomin
    0.18
     ఎక్కువ
    0.18
    Activations Density 0.030%

    No Known Activations