© 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. 23-RESID-POST-AA
    11. 51619
    Prev
    Next
    INDEX
    Explanations

    Polish

    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
     były
    -0.13
     te
    -0.12
     mogli
    -0.11
     були
    -0.11
     byly
    -0.11
     estavam
    -0.11
     seriam
    -0.11
     erano
    -0.10
     Mog
    -0.10
     voivat
    -0.10
    POSITIVE LOGITS
     jest
    0.19
     ma
    0.15
     daje
    0.14
     znajduje
    0.14
     проводить
    0.13
     będzie
    0.13
     może
    0.13
     говорить
    0.13
     pomaga
    0.12
     publ
    0.12
    Activations Density 0.006%

    No Known Activations