© 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. 1518
    Prev
    Next
    INDEX
    Explanations

    -up

    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
     Alpine
    -0.09
     práctico
    -0.08
     практика
    -0.08
     Anthrop
    -0.08
    уха
    -0.07
    維
    -0.07
     Allergy
    -0.07
    irit
    -0.07
    niga
    -0.07
     ನೀ
    -0.07
    POSITIVE LOGITS
     Math
    0.08
    Math
    0.07
    *(
    0.07
    *
    0.07
     fibro
    0.07
     loosely
    0.07
     hair
    0.07
    261
    0.07
     has
    0.07
    اخ
    0.07
    Activations Density 0.000%

    No Known Activations