© 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. 63163
    Prev
    Next
    INDEX
    Explanations

    explanations and quotations

    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
     Auschwitz
    -0.08
     thug
    -0.08
     страш
    -0.08
    CONNECTED
    -0.08
     olhos
    -0.07
    ák
    -0.07
    jours
    -0.07
     статье
    -0.07
     тонн
    -0.07
     takut
    -0.07
    POSITIVE LOGITS
     aptly
    0.08
     natural
    0.08
     literally
    0.08
     stacked
    0.08
     seiner
    0.08
     metaphor
    0.07
     literal
    0.07
     ('
    0.07
     jälle
    0.07
    heri
    0.07
    Activations Density 0.165%

    No Known Activations