© 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. 21599
    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
     (
    -0.11
    ;
    -0.11
    ,
    -0.10
    （
    -0.10
     Congrats
    -0.10
     finally
    -0.10
     ((
    -0.10
     it'll
    -0.10
     --
    -0.10
     //
    -0.10
    POSITIVE LOGITS
     implications
    0.15
    Impact
    0.15
     impact
    0.15
    Role
    0.14
     role
    0.14
     Impact
    0.13
     влияние
    0.13
    Challenges
    0.13
     Role
    0.13
     роль
    0.13
    Activations Density 0.058%

    No Known Activations