© 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. 71321
    Prev
    Next
    INDEX
    Explanations

    software libraries and linking

    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
     SWOT
    -0.10
     compass
    -0.09
     panor
    -0.09
    แด
    -0.08
     elongated
    -0.08
     hết
    -0.08
     lunes
    -0.08
     обс
    -0.08
     مربع
    -0.07
     north
    -0.07
    POSITIVE LOGITS
    cdecl
    0.14
     libc
    0.13
    libraries
    0.11
    stdcall
    0.11
     libs
    0.11
    Libraries
    0.10
    _stub
    0.10
    DLL
    0.10
    /libs
    0.10
    callee
    0.10
    Activations Density 0.010%

    No Known Activations