© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 12725
    Prev
    Next
    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ప్రయ
    -0.09
     ശ
    -0.08
    川
    -0.08
     visc
    -0.08
     freight
    -0.08
     శ
    -0.08
     Ionic
    -0.08
    _pub
    -0.08
     ഫ്ര
    -0.07
    .use
    -0.07
    POSITIVE LOGITS
    arith
    0.08
     Mm
    0.08
     ery
    0.08
    जर
    0.08
     postseason
    0.08
     Julian
    0.07
     JES
    0.07
    கு
    0.07
     Yoo
    0.07
     YES
    0.07
    Activations Density 0.105%

    No Known Activations