© 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. 11-RESID-POST-AA
    11. 70538
    Prev
    Next
    INDEX
    Explanations

    word manipulation

    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
    lighet
    -0.09
    ligt
    -0.08
     الأسرة
    -0.08
    riors
    -0.08
    lige
    -0.07
     મુજબ
    -0.07
    meniz
    -0.07
    azing
    -0.07
    periode
    -0.07
    kunde
    -0.07
    POSITIVE LOGITS
     inadvert
    0.11
     inadvertently
    0.10
     mistaken
    0.09
     falsely
    0.09
     echo
    0.09
     mistakenly
    0.08
     unrelated
    0.08
     innoc
    0.08
     unint
    0.08
     accidentally
    0.08
    Activations Density 0.007%

    No Known Activations