© 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. 18627
    Prev
    Next
    INDEX
    Explanations

    and

    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
     feminism
    -0.08
    .Track
    -0.08
    ులతో
    -0.08
    ofen
    -0.08
    _ex
    -0.08
    aksan
    -0.08
    _func
    -0.08
    uhn
    -0.08
    üe
    -0.08
    .Database
    -0.08
    POSITIVE LOGITS
     fourth
    0.21
     third
    0.21
     last
    0.20
     fifth
    0.19
     ninth
    0.18
     seventh
    0.17
    第四
    0.17
    third
    0.17
     sixth
    0.17
     tenth
    0.17
    Activations Density 0.014%

    No Known Activations