© 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. 19-RESID-POST-AA
    11. 102885
    Prev
    Next
    INDEX
    Explanations

    colors

    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
     Veel
    -0.08
    -urlencoded
    -0.07
    crast
    -0.07
     forgive
    -0.07
     Predictions
    -0.07
     bargain
    -0.07
     오후
    -0.07
     penting
    -0.07
    ебі
    -0.07
    acies
    -0.07
    POSITIVE LOGITS
     distinctive
    0.16
    颜色
    0.16
     distinct
    0.15
     colors
    0.15
     coloration
    0.15
     kleur
    0.14
     Farbe
    0.14
     रंग
    0.14
     warna
    0.14
     labels
    0.14
    Activations Density 0.021%

    No Known Activations