© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 113592
    Prev
    Next
    INDEX
    Explanations

    Avoiding certain words/characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vertrauen
    -0.09
     percaya
    -0.09
     Waxa
    -0.08
     possibilidades
    -0.08
     legít
    -0.08
     confiance
    -0.08
     realistic
    -0.08
    દર્શન
    -0.08
     Dengan
    -0.08
     waxaad
    -0.08
    POSITIVE LOGITS
     inadvert
    0.14
     inadvertently
    0.11
     unintended
    0.11
     accidental
    0.10
     accidentally
    0.10
     unwanted
    0.10
     unnoticed
    0.09
     শব্দ
    0.09
    Check
    0.09
     stray
    0.09
    Activations Density 0.010%

    No Known Activations