© 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. 18444
    Prev
    Next
    INDEX
    Explanations

    German words

    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
     Ẹ
    -0.11
    Но
    -0.11
    jų
    -0.10
     Awọn
    -0.10
    ijų
    -0.10
     Җ
    -0.10
     Nhưng
    -0.10
    Awọn
    -0.10
    Ệ
    -0.10
     Trong
    -0.10
    POSITIVE LOGITS
     wichtig
    0.09
     gleich
    0.09
     bedeut
    0.09
     schme
    0.08
     mittel
    0.08
     Braun
    0.08
     charakter
    0.08
     musst
    0.07
     Wenn
    0.07
     wichtiger
    0.07
    Activations Density 0.024%

    No Known Activations