© 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. 19586
    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
    Materia
    -0.09
     bygge
    -0.08
     ברח
    -0.08
    ോസ
    -0.08
    .Center
    -0.08
     jeśli
    -0.08
    firmasi
    -0.08
     kalau
    -0.08
     dacă
    -0.08
    /User
    -0.08
    POSITIVE LOGITS
    得
    0.16
     得
    0.14
     resultant
    0.13
     obtain
    0.13
     elde
    0.13
     얻
    0.13
     resulting
    0.12
     Obt
    0.12
     obtaining
    0.12
     obtained
    0.12
    Activations Density 0.006%

    No Known Activations