© 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. 70297
    Prev
    Next
    INDEX
    Explanations

    animals

    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
    uri
    -0.08
    BV
    -0.08
     optim
    -0.07
    (up
    -0.07
    Gen
    -0.07
    OBS
    -0.07
    ส่ง
    -0.07
    test
    -0.07
    LOPT
    -0.07
    (test
    -0.07
    POSITIVE LOGITS
     oppervlak
    0.09
     podpis
    0.09
     crema
    0.09
     shoreline
    0.09
     Oberfläche
    0.09
    絲
    0.08
     Heimat
    0.08
     поверхность
    0.08
     finde
    0.08
     tomonidan
    0.08
    Activations Density 0.032%

    No Known Activations