Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 1615
    Prev
    Next
    INDEX
    Explanations

    to

    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
     predominantly
    -0.08
    ة
    -0.08
     vive
    -0.08
    ىم
    -0.07
    驶
    -0.07
    答
    -0.07
     Magnum
    -0.07
     }),↵↵
    -0.07
     Sas
    -0.07
     tread
    -0.07
    POSITIVE LOGITS
     कहीं
    0.09
     Cana
    0.08
    CAM
    0.08
    heroes
    0.08
    Heroes
    0.07
     Camel
    0.07
     evt
    0.07
    -free
    0.07
    comes
    0.07
    graphql
    0.07
    Activations Density 0.033%

    No Known Activations