© 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. 18334
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     fix
    -0.08
     fixing
    -0.08
    怎么办
    -0.08
    成本
    -0.08
    =np
    -0.08
     donnant
    -0.07
     sech
    -0.07
     fixes
    -0.07
    хоз
    -0.07
    ifun
    -0.07
    POSITIVE LOGITS
    Palindrome
    0.12
     Congratulations
    0.11
     判
    0.11
     정말
    0.11
    Congratulations
    0.11
     definately
    0.10
     여부
    0.10
     является
    0.10
     是
    0.10
     입력
    0.10
    Activations Density 0.008%

    No Known Activations