© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18233
    Prev
    Next
    INDEX
    Explanations

    "должно/해야"

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     necessidade
    -0.12
     behöver
    -0.11
     need
    -0.11
    需要
    -0.11
     tarvit
    -0.11
     trenger
    -0.11
     necesitan
    -0.10
     bezwen
    -0.10
     necessidades
    -0.10
     requires
    -0.10
    POSITIVE LOGITS
     olema
    0.20
     быть
    0.19
     быць
    0.18
     být
    0.17
     להיות
    0.17
     być
    0.16
     būti
    0.16
     essere
    0.16
     помнить
    0.16
     être
    0.15
    Activations Density 0.010%

    No Known Activations