© 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. 23-RESID-POST-AA
    11. 48154
    Prev
    Next
    INDEX
    Explanations

    поб

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     평
    -0.07
     stam
    -0.07
    вести
    -0.07
    berg
    -0.07
     cod
    -0.07
    baum
    -0.07
    cod
    -0.07
    -0.07
     embrace
    -0.07
    brace
    -0.07
    POSITIVE LOGITS
    очных
    0.16
    очным
    0.16
    очные
    0.16
    очный
    0.15
    очное
    0.15
    очная
    0.14
    очную
    0.13
    ольше
    0.12
    очного
    0.12
    очной
    0.12
    Activations Density 0.001%

    No Known Activations